LinuxPPC-Dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v5 05/31] pseries/fadump: introduce callbacks for platform specific operations
From: Hari Bathini @ 2019-08-20 12:04 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: Ananth N Mavinakayanahalli, Mahesh J Salgaonkar, Vasant Hegde,
	Oliver, Nicholas Piggin, Daniel Axtens
In-Reply-To: <156630261682.8896.3418665808003586786.stgit@hbathini.in.ibm.com>

Introduce callback functions for platform specific operations like
register, unregister, invalidate & such. Also, define place-holders
for the same on pSeries platform.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
 arch/powerpc/kernel/fadump-common.h          |   26 +++++
 arch/powerpc/kernel/fadump.c                 |   47 +--------
 arch/powerpc/platforms/pseries/Makefile      |    1 
 arch/powerpc/platforms/pseries/rtas-fadump.c |  129 ++++++++++++++++++++++++++
 4 files changed, 159 insertions(+), 44 deletions(-)
 create mode 100644 arch/powerpc/platforms/pseries/rtas-fadump.c

diff --git a/arch/powerpc/kernel/fadump-common.h b/arch/powerpc/kernel/fadump-common.h
index 93bc471..898d0e8 100644
--- a/arch/powerpc/kernel/fadump-common.h
+++ b/arch/powerpc/kernel/fadump-common.h
@@ -80,6 +80,9 @@ struct fad_crash_memory_ranges {
 	unsigned long long	size;
 };
 
+/* Platform specific callback functions */
+struct fadump_ops;
+
 /* Firmware-assisted dump configuration details. */
 struct fw_dump {
 	unsigned long	reserve_dump_area_start;
@@ -102,6 +105,20 @@ struct fw_dump {
 	unsigned long	dump_active:1;
 	unsigned long	dump_registered:1;
 	unsigned long	nocma:1;
+
+	struct fadump_ops		*ops;
+};
+
+struct fadump_ops {
+	ulong	(*fadump_init_mem_struct)(struct fw_dump *fadump_config);
+	int	(*fadump_register)(struct fw_dump *fadump_config);
+	int	(*fadump_unregister)(struct fw_dump *fadump_config);
+	int	(*fadump_invalidate)(struct fw_dump *fadump_config);
+	int	(*fadump_process)(struct fw_dump *fadump_config);
+	void	(*fadump_region_show)(struct fw_dump *fadump_config,
+				      struct seq_file *m);
+	void	(*fadump_trigger)(struct fadump_crash_info_header *fdh,
+				  const char *msg);
 };
 
 /* Helper functions */
@@ -112,4 +129,13 @@ void fadump_update_elfcore_header(struct fw_dump *fadump_config, char *bufp);
 int is_fadump_boot_mem_contiguous(struct fw_dump *fadump_conf);
 int is_fadump_reserved_mem_contiguous(struct fw_dump *fadump_conf);
 
+#ifdef CONFIG_PPC_PSERIES
+extern int rtas_fadump_dt_scan(struct fw_dump *fadump_config, ulong node);
+#else
+static inline int rtas_fadump_dt_scan(struct fw_dump *fadump_config, ulong node)
+{
+	return 1;
+}
+#endif
+
 #endif /* __PPC64_FA_DUMP_INTERNAL_H__ */
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 23c0ca0..99d5def 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -112,24 +112,12 @@ static int __init fadump_cma_init(void) { return 1; }
 int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
 				      int depth, void *data)
 {
-	const __be32 *sections;
-	int i, num_sections;
-	int size;
-	const __be32 *token;
+	int ret;
 
 	if (depth != 1 || strcmp(uname, "rtas") != 0)
 		return 0;
 
-	/*
-	 * Check if Firmware Assisted dump is supported. if yes, check
-	 * if dump has been initiated on last reboot.
-	 */
-	token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
-	if (!token)
-		return 1;
-
-	fw_dump.fadump_supported = 1;
-	fw_dump.ibm_configure_kernel_dump = be32_to_cpu(*token);
+	ret = rtas_fadump_dt_scan(&fw_dump, node);
 
 	/*
 	 * The 'ibm,kernel-dump' rtas node is present only if there is
@@ -139,36 +127,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
 	if (fdm_active)
 		fw_dump.dump_active = 1;
 
-	/* Get the sizes required to store dump data for the firmware provided
-	 * dump sections.
-	 * For each dump section type supported, a 32bit cell which defines
-	 * the ID of a supported section followed by two 32 bit cells which
-	 * gives teh size of the section in bytes.
-	 */
-	sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
-					&size);
-
-	if (!sections)
-		return 1;
-
-	num_sections = size / (3 * sizeof(u32));
-
-	for (i = 0; i < num_sections; i++, sections += 3) {
-		u32 type = (u32)of_read_number(sections, 1);
-
-		switch (type) {
-		case RTAS_FADUMP_CPU_STATE_DATA:
-			fw_dump.cpu_state_data_size =
-					of_read_ulong(&sections[1], 2);
-			break;
-		case RTAS_FADUMP_HPTE_REGION:
-			fw_dump.hpte_region_size =
-					of_read_ulong(&sections[1], 2);
-			break;
-		}
-	}
-
-	return 1;
+	return ret;
 }
 
 /*
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index ab3d59a..e248724 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_IBMVIO)		+= vio.o
 obj-$(CONFIG_IBMEBUS)		+= ibmebus.o
 obj-$(CONFIG_PAPR_SCM)		+= papr_scm.o
 obj-$(CONFIG_PPC_SPLPAR)	+= vphn.o
+obj-$(CONFIG_FA_DUMP)		+= rtas-fadump.o
 
 ifdef CONFIG_PPC_PSERIES
 obj-$(CONFIG_SUSPEND)		+= suspend.o
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.c b/arch/powerpc/platforms/pseries/rtas-fadump.c
new file mode 100644
index 0000000..b77d738
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Firmware-Assisted Dump support on POWERVM platform.
+ *
+ * Copyright 2011, IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.ibm.com>
+ *
+ * Copyright 2019, IBM Corp.
+ * Author: Hari Bathini <hbathini@linux.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "rtas fadump: " fmt
+
+#include <linux/string.h>
+#include <linux/memblock.h>
+#include <linux/delay.h>
+#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
+
+#include <asm/page.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+#include <asm/fadump.h>
+
+#include "../../kernel/fadump-common.h"
+#include "rtas-fadump.h"
+
+static ulong rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf)
+{
+	return fadump_conf->reserve_dump_area_start;
+}
+
+static int rtas_fadump_register(struct fw_dump *fadump_conf)
+{
+	return -EIO;
+}
+
+static int rtas_fadump_unregister(struct fw_dump *fadump_conf)
+{
+	return -EIO;
+}
+
+static int rtas_fadump_invalidate(struct fw_dump *fadump_conf)
+{
+	return -EIO;
+}
+
+/*
+ * Validate and process the dump data stored by firmware before exporting
+ * it through '/proc/vmcore'.
+ */
+static int __init rtas_fadump_process(struct fw_dump *fadump_conf)
+{
+	return -EINVAL;
+}
+
+static void rtas_fadump_region_show(struct fw_dump *fadump_conf,
+				    struct seq_file *m)
+{
+}
+
+static void rtas_fadump_trigger(struct fadump_crash_info_header *fdh,
+				const char *msg)
+{
+	/* Call ibm,os-term rtas call to trigger firmware assisted dump */
+	rtas_os_term((char *)msg);
+}
+
+static struct fadump_ops rtas_fadump_ops = {
+	.fadump_init_mem_struct		= rtas_fadump_init_mem_struct,
+	.fadump_register		= rtas_fadump_register,
+	.fadump_unregister		= rtas_fadump_unregister,
+	.fadump_invalidate		= rtas_fadump_invalidate,
+	.fadump_process			= rtas_fadump_process,
+	.fadump_region_show		= rtas_fadump_region_show,
+	.fadump_trigger			= rtas_fadump_trigger,
+};
+
+int __init rtas_fadump_dt_scan(struct fw_dump *fadump_conf, ulong node)
+{
+	const __be32 *sections;
+	int i, num_sections;
+	int size;
+	const __be32 *token;
+
+	/*
+	 * Check if Firmware Assisted dump is supported. if yes, check
+	 * if dump has been initiated on last reboot.
+	 */
+	token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
+	if (!token)
+		return 1;
+
+	fadump_conf->ibm_configure_kernel_dump = be32_to_cpu(*token);
+	fadump_conf->ops		= &rtas_fadump_ops;
+	fadump_conf->fadump_supported	= 1;
+
+	/* Get the sizes required to store dump data for the firmware provided
+	 * dump sections.
+	 * For each dump section type supported, a 32bit cell which defines
+	 * the ID of a supported section followed by two 32 bit cells which
+	 * gives the size of the section in bytes.
+	 */
+	sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
+					&size);
+
+	if (!sections)
+		return 1;
+
+	num_sections = size / (3 * sizeof(u32));
+
+	for (i = 0; i < num_sections; i++, sections += 3) {
+		u32 type = (u32)of_read_number(sections, 1);
+
+		switch (type) {
+		case RTAS_FADUMP_CPU_STATE_DATA:
+			fadump_conf->cpu_state_data_size =
+					of_read_ulong(&sections[1], 2);
+			break;
+		case RTAS_FADUMP_HPTE_REGION:
+			fadump_conf->hpte_region_size =
+					of_read_ulong(&sections[1], 2);
+			break;
+		}
+	}
+
+	return 1;
+}


^ permalink raw reply related

* [PATCH v5 04/31] pseries/fadump: move rtas specific definitions to platform code
From: Hari Bathini @ 2019-08-20 12:04 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: Ananth N Mavinakayanahalli, Mahesh J Salgaonkar, Vasant Hegde,
	Oliver, Nicholas Piggin, Daniel Axtens
In-Reply-To: <156630261682.8896.3418665808003586786.stgit@hbathini.in.ibm.com>

Currently, FADump is only supported on pSeries but that is going to
change soon with FADump support being added on PowerNV platform. So,
move rtas specific definitions to platform code to allow FADump
to have multiple platforms support.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
 arch/powerpc/include/asm/fadump.h            |  112 --------------------------
 arch/powerpc/kernel/fadump-common.h          |   20 ++++-
 arch/powerpc/kernel/fadump.c                 |   90 +++++++++++----------
 arch/powerpc/platforms/pseries/rtas-fadump.h |  103 ++++++++++++++++++++++++
 4 files changed, 170 insertions(+), 155 deletions(-)
 create mode 100644 arch/powerpc/platforms/pseries/rtas-fadump.h

diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 75179497..e608d34 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -11,116 +11,8 @@
 
 #ifdef CONFIG_FA_DUMP
 
-/* Firmware provided dump sections */
-#define FADUMP_CPU_STATE_DATA	0x0001
-#define FADUMP_HPTE_REGION	0x0002
-#define FADUMP_REAL_MODE_REGION	0x0011
-
-/* Dump request flag */
-#define FADUMP_REQUEST_FLAG	0x00000001
-
-/* Dump status flag */
-#define FADUMP_ERROR_FLAG	0x2000
-
-#define FADUMP_CPU_ID_MASK	((1UL << 32) - 1)
-
-#define CPU_UNKNOWN		(~((u32)0))
-
-/* Utility macros */
-#define SKIP_TO_NEXT_CPU(reg_entry)					\
-({									\
-	while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND"))	\
-		reg_entry++;						\
-	reg_entry++;							\
-})
-
 extern int crashing_cpu;
 
-/* Kernel Dump section info */
-struct fadump_section {
-	__be32	request_flag;
-	__be16	source_data_type;
-	__be16	error_flags;
-	__be64	source_address;
-	__be64	source_len;
-	__be64	bytes_dumped;
-	__be64	destination_address;
-};
-
-/* ibm,configure-kernel-dump header. */
-struct fadump_section_header {
-	__be32	dump_format_version;
-	__be16	dump_num_sections;
-	__be16	dump_status_flag;
-	__be32	offset_first_dump_section;
-
-	/* Fields for disk dump option. */
-	__be32	dd_block_size;
-	__be64	dd_block_offset;
-	__be64	dd_num_blocks;
-	__be32	dd_offset_disk_path;
-
-	/* Maximum time allowed to prevent an automatic dump-reboot. */
-	__be32	max_time_auto;
-};
-
-/*
- * Firmware Assisted dump memory structure. This structure is required for
- * registering future kernel dump with power firmware through rtas call.
- *
- * No disk dump option. Hence disk dump path string section is not included.
- */
-struct fadump_mem_struct {
-	struct fadump_section_header	header;
-
-	/* Kernel dump sections */
-	struct fadump_section		cpu_state_data;
-	struct fadump_section		hpte_region;
-	struct fadump_section		rmr_region;
-};
-
-/*
- * Copy the ascii values for first 8 characters from a string into u64
- * variable at their respective indexes.
- * e.g.
- *  The string "FADMPINF" will be converted into 0x4641444d50494e46
- */
-static inline u64 str_to_u64(const char *str)
-{
-	u64 val = 0;
-	int i;
-
-	for (i = 0; i < sizeof(val); i++)
-		val = (*str) ? (val << 8) | *str++ : val << 8;
-	return val;
-}
-#define STR_TO_HEX(x)	str_to_u64(x)
-#define REG_ID(x)	str_to_u64(x)
-
-#define REGSAVE_AREA_MAGIC		STR_TO_HEX("REGSAVE")
-
-/* The firmware-assisted dump format.
- *
- * The register save area is an area in the partition's memory used to preserve
- * the register contents (CPU state data) for the active CPUs during a firmware
- * assisted dump. The dump format contains register save area header followed
- * by register entries. Each list of registers for a CPU starts with
- * "CPUSTRT" and ends with "CPUEND".
- */
-
-/* Register save area header. */
-struct fadump_reg_save_area_header {
-	__be64		magic_number;
-	__be32		version;
-	__be32		num_cpu_offset;
-};
-
-/* Register entry. */
-struct fadump_reg_entry {
-	__be64		reg_id;
-	__be64		reg_value;
-};
-
 extern int is_fadump_memory_area(u64 addr, ulong size);
 extern int early_init_dt_scan_fw_dump(unsigned long node,
 		const char *uname, int depth, void *data);
@@ -136,5 +28,5 @@ static inline int is_fadump_active(void) { return 0; }
 static inline int should_fadump_crash(void) { return 0; }
 static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
 static inline void fadump_cleanup(void) { }
-#endif
-#endif
+#endif /* !CONFIG_FA_DUMP */
+#endif /* __PPC64_FA_DUMP_H__ */
diff --git a/arch/powerpc/kernel/fadump-common.h b/arch/powerpc/kernel/fadump-common.h
index 54328ef..93bc471 100644
--- a/arch/powerpc/kernel/fadump-common.h
+++ b/arch/powerpc/kernel/fadump-common.h
@@ -46,7 +46,25 @@
 #define FADUMP_UNREGISTER		2
 #define FADUMP_INVALIDATE		3
 
-#define FADUMP_CRASH_INFO_MAGIC		str_to_u64("FADMPINF")
+/*
+ * Copy the ascii values for first 8 characters from a string into u64
+ * variable at their respective indexes.
+ * e.g.
+ *  The string "FADMPINF" will be converted into 0x4641444d50494e46
+ */
+static inline u64 fadump_str_to_u64(const char *str)
+{
+	u64 val = 0;
+	int i;
+
+	for (i = 0; i < sizeof(val); i++)
+		val = (*str) ? (val << 8) | *str++ : val << 8;
+	return val;
+}
+
+#define FADUMP_CPU_UNKNOWN		(~((u32)0))
+
+#define FADUMP_CRASH_INFO_MAGIC		fadump_str_to_u64("FADMPINF")
 
 /* fadump crash info structure */
 struct fadump_crash_info_header {
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 40e5e96..23c0ca0 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -33,10 +33,11 @@
 #include <asm/setup.h>
 
 #include "fadump-common.h"
+#include "../platforms/pseries/rtas-fadump.h"
 
 static struct fw_dump fw_dump;
-static struct fadump_mem_struct fdm;
-static const struct fadump_mem_struct *fdm_active;
+static struct rtas_fadump_mem_struct fdm;
+static const struct rtas_fadump_mem_struct *fdm_active;
 
 static DEFINE_MUTEX(fadump_mutex);
 struct fad_crash_memory_ranges *crash_memory_ranges;
@@ -156,11 +157,11 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
 		u32 type = (u32)of_read_number(sections, 1);
 
 		switch (type) {
-		case FADUMP_CPU_STATE_DATA:
+		case RTAS_FADUMP_CPU_STATE_DATA:
 			fw_dump.cpu_state_data_size =
 					of_read_ulong(&sections[1], 2);
 			break;
-		case FADUMP_HPTE_REGION:
+		case RTAS_FADUMP_HPTE_REGION:
 			fw_dump.hpte_region_size =
 					of_read_ulong(&sections[1], 2);
 			break;
@@ -219,20 +220,20 @@ static void fadump_show_config(void)
 	pr_debug("Boot memory size  : %lx\n", fw_dump.boot_memory_size);
 }
 
-static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
+static unsigned long init_fadump_mem_struct(struct rtas_fadump_mem_struct *fdm,
 				unsigned long addr)
 {
 	if (!fdm)
 		return 0;
 
-	memset(fdm, 0, sizeof(struct fadump_mem_struct));
+	memset(fdm, 0, sizeof(struct rtas_fadump_mem_struct));
 	addr = addr & PAGE_MASK;
 
 	fdm->header.dump_format_version = cpu_to_be32(0x00000001);
 	fdm->header.dump_num_sections = cpu_to_be16(3);
 	fdm->header.dump_status_flag = 0;
 	fdm->header.offset_first_dump_section =
-		cpu_to_be32((u32)offsetof(struct fadump_mem_struct, cpu_state_data));
+		cpu_to_be32((u32)offsetof(struct rtas_fadump_mem_struct, cpu_state_data));
 
 	/*
 	 * Fields for disk dump option.
@@ -248,24 +249,24 @@ static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
 
 	/* Kernel dump sections */
 	/* cpu state data section. */
-	fdm->cpu_state_data.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
-	fdm->cpu_state_data.source_data_type = cpu_to_be16(FADUMP_CPU_STATE_DATA);
+	fdm->cpu_state_data.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+	fdm->cpu_state_data.source_data_type = cpu_to_be16(RTAS_FADUMP_CPU_STATE_DATA);
 	fdm->cpu_state_data.source_address = 0;
 	fdm->cpu_state_data.source_len = cpu_to_be64(fw_dump.cpu_state_data_size);
 	fdm->cpu_state_data.destination_address = cpu_to_be64(addr);
 	addr += fw_dump.cpu_state_data_size;
 
 	/* hpte region section */
-	fdm->hpte_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
-	fdm->hpte_region.source_data_type = cpu_to_be16(FADUMP_HPTE_REGION);
+	fdm->hpte_region.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+	fdm->hpte_region.source_data_type = cpu_to_be16(RTAS_FADUMP_HPTE_REGION);
 	fdm->hpte_region.source_address = 0;
 	fdm->hpte_region.source_len = cpu_to_be64(fw_dump.hpte_region_size);
 	fdm->hpte_region.destination_address = cpu_to_be64(addr);
 	addr += fw_dump.hpte_region_size;
 
 	/* RMA region section */
-	fdm->rmr_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG);
-	fdm->rmr_region.source_data_type = cpu_to_be16(FADUMP_REAL_MODE_REGION);
+	fdm->rmr_region.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG);
+	fdm->rmr_region.source_data_type = cpu_to_be16(RTAS_FADUMP_REAL_MODE_REGION);
 	fdm->rmr_region.source_address = cpu_to_be64(RMA_START);
 	fdm->rmr_region.source_len = cpu_to_be64(fw_dump.boot_memory_size);
 	fdm->rmr_region.destination_address = cpu_to_be64(addr);
@@ -536,7 +537,7 @@ static int __init early_fadump_reserve_mem(char *p)
 }
 early_param("fadump_reserve_mem", early_fadump_reserve_mem);
 
-static int register_fw_dump(struct fadump_mem_struct *fdm)
+static int register_fw_dump(struct rtas_fadump_mem_struct *fdm)
 {
 	int rc, err;
 	unsigned int wait_time;
@@ -547,7 +548,7 @@ static int register_fw_dump(struct fadump_mem_struct *fdm)
 	do {
 		rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
 			FADUMP_REGISTER, fdm,
-			sizeof(struct fadump_mem_struct));
+			sizeof(struct rtas_fadump_mem_struct));
 
 		wait_time = rtas_busy_delay_time(rc);
 		if (wait_time)
@@ -643,7 +644,7 @@ static inline int fadump_gpr_index(u64 id)
 	int i = -1;
 	char str[3];
 
-	if ((id & GPR_MASK) == REG_ID("GPR")) {
+	if ((id & GPR_MASK) == fadump_str_to_u64("GPR")) {
 		/* get the digits at the end */
 		id &= ~GPR_MASK;
 		id >>= 24;
@@ -665,30 +666,30 @@ static inline void fadump_set_regval(struct pt_regs *regs, u64 reg_id,
 	i = fadump_gpr_index(reg_id);
 	if (i >= 0)
 		regs->gpr[i] = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("NIA"))
+	else if (reg_id == fadump_str_to_u64("NIA"))
 		regs->nip = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("MSR"))
+	else if (reg_id == fadump_str_to_u64("MSR"))
 		regs->msr = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("CTR"))
+	else if (reg_id == fadump_str_to_u64("CTR"))
 		regs->ctr = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("LR"))
+	else if (reg_id == fadump_str_to_u64("LR"))
 		regs->link = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("XER"))
+	else if (reg_id == fadump_str_to_u64("XER"))
 		regs->xer = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("CR"))
+	else if (reg_id == fadump_str_to_u64("CR"))
 		regs->ccr = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("DAR"))
+	else if (reg_id == fadump_str_to_u64("DAR"))
 		regs->dar = (unsigned long)reg_val;
-	else if (reg_id == REG_ID("DSISR"))
+	else if (reg_id == fadump_str_to_u64("DSISR"))
 		regs->dsisr = (unsigned long)reg_val;
 }
 
-static struct fadump_reg_entry*
-fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
+static struct rtas_fadump_reg_entry*
+fadump_read_registers(struct rtas_fadump_reg_entry *reg_entry, struct pt_regs *regs)
 {
 	memset(regs, 0, sizeof(struct pt_regs));
 
-	while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND")) {
+	while (be64_to_cpu(reg_entry->reg_id) != fadump_str_to_u64("CPUEND")) {
 		fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id),
 					be64_to_cpu(reg_entry->reg_value));
 		reg_entry++;
@@ -711,10 +712,10 @@ fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
  * state from fadump crash info structure populated by first kernel at the
  * time of crash.
  */
-static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
+static int __init fadump_build_cpu_notes(const struct rtas_fadump_mem_struct *fdm)
 {
-	struct fadump_reg_save_area_header *reg_header;
-	struct fadump_reg_entry *reg_entry;
+	struct rtas_fadump_reg_save_area_header *reg_header;
+	struct rtas_fadump_reg_entry *reg_entry;
 	struct fadump_crash_info_header *fdh = NULL;
 	void *vaddr;
 	unsigned long addr;
@@ -729,7 +730,8 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
 	vaddr = __va(addr);
 
 	reg_header = vaddr;
-	if (be64_to_cpu(reg_header->magic_number) != REGSAVE_AREA_MAGIC) {
+	if (be64_to_cpu(reg_header->magic_number) !=
+	    fadump_str_to_u64("REGSAVE")) {
 		printk(KERN_ERR "Unable to read register save area.\n");
 		return -ENOENT;
 	}
@@ -741,7 +743,7 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
 	num_cpus = be32_to_cpu(*((__be32 *)(vaddr)));
 	pr_debug("NumCpus     : %u\n", num_cpus);
 	vaddr += sizeof(u32);
-	reg_entry = (struct fadump_reg_entry *)vaddr;
+	reg_entry = (struct rtas_fadump_reg_entry *)vaddr;
 
 	/* Allocate buffer to hold cpu crash notes. */
 	fw_dump.cpu_notes_buf_size = num_cpus * sizeof(note_buf_t);
@@ -761,22 +763,22 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
 		fdh = __va(fw_dump.fadumphdr_addr);
 
 	for (i = 0; i < num_cpus; i++) {
-		if (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUSTRT")) {
+		if (be64_to_cpu(reg_entry->reg_id) != fadump_str_to_u64("CPUSTRT")) {
 			printk(KERN_ERR "Unable to read CPU state data\n");
 			rc = -ENOENT;
 			goto error_out;
 		}
 		/* Lower 4 bytes of reg_value contains logical cpu id */
-		cpu = be64_to_cpu(reg_entry->reg_value) & FADUMP_CPU_ID_MASK;
+		cpu = be64_to_cpu(reg_entry->reg_value) & RTAS_FADUMP_CPU_ID_MASK;
 		if (fdh && !cpumask_test_cpu(cpu, &fdh->online_mask)) {
-			SKIP_TO_NEXT_CPU(reg_entry);
+			RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry);
 			continue;
 		}
 		pr_debug("Reading register data for cpu %d...\n", cpu);
 		if (fdh && fdh->crashing_cpu == cpu) {
 			regs = fdh->regs;
 			note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
-			SKIP_TO_NEXT_CPU(reg_entry);
+			RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry);
 		} else {
 			reg_entry++;
 			reg_entry = fadump_read_registers(reg_entry, &regs);
@@ -805,7 +807,7 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
  * Validate and process the dump data stored by firmware before exporting
  * it through '/proc/vmcore'.
  */
-static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
+static int __init process_fadump(const struct rtas_fadump_mem_struct *fdm_active)
 {
 	struct fadump_crash_info_header *fdh;
 	int rc = 0;
@@ -814,7 +816,7 @@ static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
 		return -EINVAL;
 
 	/* Check if the dump data is valid. */
-	if ((be16_to_cpu(fdm_active->header.dump_status_flag) == FADUMP_ERROR_FLAG) ||
+	if ((be16_to_cpu(fdm_active->header.dump_status_flag) == RTAS_FADUMP_ERROR_FLAG) ||
 			(fdm_active->cpu_state_data.error_flags != 0) ||
 			(fdm_active->rmr_region.error_flags != 0)) {
 		printk(KERN_ERR "Dump taken by platform is not valid\n");
@@ -1145,7 +1147,7 @@ static unsigned long init_fadump_header(unsigned long addr)
 	fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
 	fdh->elfcorehdr_addr = addr;
 	/* We will set the crashing cpu id in crash_fadump() during crash. */
-	fdh->crashing_cpu = CPU_UNKNOWN;
+	fdh->crashing_cpu = FADUMP_CPU_UNKNOWN;
 
 	return addr;
 }
@@ -1179,7 +1181,7 @@ static int register_fadump(void)
 	return register_fw_dump(&fdm);
 }
 
-static int fadump_unregister_dump(struct fadump_mem_struct *fdm)
+static int fadump_unregister_dump(struct rtas_fadump_mem_struct *fdm)
 {
 	int rc = 0;
 	unsigned int wait_time;
@@ -1190,7 +1192,7 @@ static int fadump_unregister_dump(struct fadump_mem_struct *fdm)
 	do {
 		rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
 			FADUMP_UNREGISTER, fdm,
-			sizeof(struct fadump_mem_struct));
+			sizeof(struct rtas_fadump_mem_struct));
 
 		wait_time = rtas_busy_delay_time(rc);
 		if (wait_time)
@@ -1206,7 +1208,7 @@ static int fadump_unregister_dump(struct fadump_mem_struct *fdm)
 	return 0;
 }
 
-static int fadump_invalidate_dump(const struct fadump_mem_struct *fdm)
+static int fadump_invalidate_dump(const struct rtas_fadump_mem_struct *fdm)
 {
 	int rc = 0;
 	unsigned int wait_time;
@@ -1217,7 +1219,7 @@ static int fadump_invalidate_dump(const struct fadump_mem_struct *fdm)
 	do {
 		rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
 			FADUMP_INVALIDATE, fdm,
-			sizeof(struct fadump_mem_struct));
+			sizeof(struct rtas_fadump_mem_struct));
 
 		wait_time = rtas_busy_delay_time(rc);
 		if (wait_time)
@@ -1438,7 +1440,7 @@ static ssize_t fadump_register_store(struct kobject *kobj,
 
 static int fadump_region_show(struct seq_file *m, void *private)
 {
-	const struct fadump_mem_struct *fdm_ptr;
+	const struct rtas_fadump_mem_struct *fdm_ptr;
 
 	if (!fw_dump.fadump_enabled)
 		return 0;
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.h b/arch/powerpc/platforms/pseries/rtas-fadump.h
new file mode 100644
index 0000000..a3a2918
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Firmware-Assisted Dump support on POWERVM platform.
+ *
+ * Copyright 2011, IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.ibm.com>
+ *
+ * Copyright 2019, IBM Corp.
+ * Author: Hari Bathini <hbathini@linux.ibm.com>
+ */
+
+#ifndef __PPC64_RTAS_FA_DUMP_H__
+#define __PPC64_RTAS_FA_DUMP_H__
+
+/* Firmware provided dump sections */
+#define RTAS_FADUMP_CPU_STATE_DATA	0x0001
+#define RTAS_FADUMP_HPTE_REGION		0x0002
+#define RTAS_FADUMP_REAL_MODE_REGION	0x0011
+
+/* Dump request flag */
+#define RTAS_FADUMP_REQUEST_FLAG	0x00000001
+
+/* Dump status flag */
+#define RTAS_FADUMP_ERROR_FLAG		0x2000
+
+/* Kernel Dump section info */
+struct rtas_fadump_section {
+	__be32	request_flag;
+	__be16	source_data_type;
+	__be16	error_flags;
+	__be64	source_address;
+	__be64	source_len;
+	__be64	bytes_dumped;
+	__be64	destination_address;
+};
+
+/* ibm,configure-kernel-dump header. */
+struct rtas_fadump_section_header {
+	__be32	dump_format_version;
+	__be16	dump_num_sections;
+	__be16	dump_status_flag;
+	__be32	offset_first_dump_section;
+
+	/* Fields for disk dump option. */
+	__be32	dd_block_size;
+	__be64	dd_block_offset;
+	__be64	dd_num_blocks;
+	__be32	dd_offset_disk_path;
+
+	/* Maximum time allowed to prevent an automatic dump-reboot. */
+	__be32	max_time_auto;
+};
+
+/*
+ * Firmware Assisted dump memory structure. This structure is required for
+ * registering future kernel dump with power firmware through rtas call.
+ *
+ * No disk dump option. Hence disk dump path string section is not included.
+ */
+struct rtas_fadump_mem_struct {
+	struct rtas_fadump_section_header	header;
+
+	/* Kernel dump sections */
+	struct rtas_fadump_section		cpu_state_data;
+	struct rtas_fadump_section		hpte_region;
+	struct rtas_fadump_section		rmr_region;
+};
+
+/*
+ * The firmware-assisted dump format.
+ *
+ * The register save area is an area in the partition's memory used to preserve
+ * the register contents (CPU state data) for the active CPUs during a firmware
+ * assisted dump. The dump format contains register save area header followed
+ * by register entries. Each list of registers for a CPU starts with "CPUSTRT"
+ * and ends with "CPUEND".
+ */
+
+/* Register save area header. */
+struct rtas_fadump_reg_save_area_header {
+	__be64		magic_number;
+	__be32		version;
+	__be32		num_cpu_offset;
+};
+
+/* Register entry. */
+struct rtas_fadump_reg_entry {
+	__be64		reg_id;
+	__be64		reg_value;
+};
+
+/* Utility macros */
+#define RTAS_FADUMP_SKIP_TO_NEXT_CPU(reg_entry)				\
+({									\
+	while (be64_to_cpu(reg_entry->reg_id) !=			\
+	       fadump_str_to_u64("CPUEND"))				\
+		reg_entry++;						\
+	reg_entry++;							\
+})
+
+#define RTAS_FADUMP_CPU_ID_MASK			((1UL << 32) - 1)
+
+#endif /* __PPC64_RTAS_FA_DUMP_H__ */


^ permalink raw reply related

* [PATCH v5 03/31] powerpc/fadump: Improve fadump documentation
From: Hari Bathini @ 2019-08-20 12:04 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: Ananth N Mavinakayanahalli, Mahesh J Salgaonkar, Vasant Hegde,
	Oliver, Nicholas Piggin, Daniel Axtens
In-Reply-To: <156630261682.8896.3418665808003586786.stgit@hbathini.in.ibm.com>

The figures depicting FADump's (Firmware-Assisted Dump) memory layout
are missing some finer details like different memory regions and what
they represent. Improve the documentation by updating those details.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
 Documentation/powerpc/firmware-assisted-dump.rst |   61 ++++++++++++----------
 1 file changed, 33 insertions(+), 28 deletions(-)

diff --git a/Documentation/powerpc/firmware-assisted-dump.rst b/Documentation/powerpc/firmware-assisted-dump.rst
index 9ca1283..563c021 100644
--- a/Documentation/powerpc/firmware-assisted-dump.rst
+++ b/Documentation/powerpc/firmware-assisted-dump.rst
@@ -76,8 +76,9 @@ as follows:
    there is crash data available from a previous boot. During
    the early boot OS will reserve rest of the memory above
    boot memory size effectively booting with restricted memory
-   size. This will make sure that the second kernel will not
-   touch any of the dump memory area.
+   size. This will make sure that this kernel (also, referred
+   to as second kernel or capture kernel) will not touch any
+   of the dump memory area.
 
 -  User-space tools will read /proc/vmcore to obtain the contents
    of memory, which holds the previous crashed kernel dump in ELF
@@ -128,42 +129,46 @@ space memory except the user pages that were present in CMA region::
 
   o Memory Reservation during first kernel
 
-  Low memory                                         Top of memory
-  0      boot memory size                                       |
-  |           |                |<--Reserved dump area -->|      |
-  V           V                |   Permanent Reservation |      V
-  +-----------+----------/ /---+---+----+-----------+----+------+
-  |           |                |CPU|HPTE|  DUMP     |ELF |      |
-  +-----------+----------/ /---+---+----+-----------+----+------+
-        |                                           ^
-        |                                           |
-        \                                           /
-         -------------------------------------------
-          Boot memory content gets transferred to
-          reserved area by firmware at the time of
-          crash
+  Low memory                                                Top of memory
+  0      boot memory size      |<--Reserved dump area --->|      |
+  |           |                | (Permanent Reservation)  |      |
+  V           V                |                          |      V
+  +-----------+----------/ /---+---+----+--------+---+----+------+
+  |           |                |CPU|HPTE|  DUMP  |HDR|ELF |      |
+  +-----------+----------/ /---+---+----+--------+---+----+------+
+        |                                   ^      ^
+        |                                   |      |
+        \                                   /      |
+         -----------------------------------     FADump Header
+          Boot memory content gets transferred   (meta area)
+          to reserved area by firmware at the
+          time of crash
+
                    Fig. 1
 
+
   o Memory Reservation during second kernel after crash
 
-  Low memory                                        Top of memory
-  0      boot memory size                                       |
-  |           |<------------- Reserved dump area ----------- -->|
-  V           V                                                 V
-  +-----------+----------/ /---+---+----+-----------+----+------+
-  |           |                |CPU|HPTE|  DUMP     |ELF |      |
-  +-----------+----------/ /---+---+----+-----------+----+------+
+  Low memory                                                Top of memory
+  0      boot memory size                                        |
+  |           |<----------- Crash preserved area --------------->|
+  V           V                |<-- Reserved dump area -->|      V
+  +-----------+----------/ /---+---+----+--------+---+----+------+
+  |           |                |CPU|HPTE|  DUMP  |HDR|ELF |      |
+  +-----------+----------/ /---+---+----+--------+---+----+------+
         |                                              |
         V                                              V
    Used by second                                /proc/vmcore
    kernel to boot
                    Fig. 2
 
-Currently the dump will be copied from /proc/vmcore to a
-a new file upon user intervention. The dump data available through
-/proc/vmcore will be in ELF format. Hence the existing kdump
-infrastructure (kdump scripts) to save the dump works fine with
-minor modifications.
+Currently the dump will be copied from /proc/vmcore to a new file upon
+user intervention. The dump data available through /proc/vmcore will be
+in ELF format. Hence the existing kdump infrastructure (kdump scripts)
+to save the dump works fine with minor modifications. KDump scripts on
+major Distro releases have already been modified to work seemlessly (no
+user intervention in saving the dump) when FADump is used, instead of
+KDump, as dump mechanism.
 
 The tools to examine the dump will be same as the ones
 used for kdump.


^ permalink raw reply related

* [PATCH v5 02/31] powerpc/fadump: move internal code to a new file
From: Hari Bathini @ 2019-08-20 12:04 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: Ananth N Mavinakayanahalli, Mahesh J Salgaonkar, Vasant Hegde,
	Oliver, Nicholas Piggin, Daniel Axtens
In-Reply-To: <156630261682.8896.3418665808003586786.stgit@hbathini.in.ibm.com>

Make way for refactoring platform specific FADump code by moving code
that could be referenced from multiple places to fadump-common.c file.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
 arch/powerpc/kernel/Makefile        |    2 
 arch/powerpc/kernel/fadump-common.c |  140 ++++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/fadump-common.h |    8 ++
 arch/powerpc/kernel/fadump.c        |  146 ++---------------------------------
 4 files changed, 158 insertions(+), 138 deletions(-)
 create mode 100644 arch/powerpc/kernel/fadump-common.c

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 56dfa7a..439d548 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -78,7 +78,7 @@ obj-$(CONFIG_EEH)              += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
 				  eeh_driver.o eeh_event.o eeh_sysfs.o
 obj-$(CONFIG_GENERIC_TBSYNC)	+= smp-tbsync.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
-obj-$(CONFIG_FA_DUMP)		+= fadump.o
+obj-$(CONFIG_FA_DUMP)		+= fadump.o fadump-common.o
 ifdef CONFIG_PPC32
 obj-$(CONFIG_E500)		+= idle_e500.o
 endif
diff --git a/arch/powerpc/kernel/fadump-common.c b/arch/powerpc/kernel/fadump-common.c
new file mode 100644
index 0000000..7f39e4f
--- /dev/null
+++ b/arch/powerpc/kernel/fadump-common.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Firmware-Assisted Dump internal code.
+ *
+ * Copyright 2011, IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.ibm.com>
+ *
+ * Copyright 2019, IBM Corp.
+ * Author: Hari Bathini <hbathini@linux.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "fadump: " fmt
+
+#include <linux/memblock.h>
+#include <linux/elf.h>
+#include <linux/mm.h>
+#include <linux/crash_core.h>
+
+#include "fadump-common.h"
+
+void *fadump_cpu_notes_buf_alloc(unsigned long size)
+{
+	void *vaddr;
+	struct page *page;
+	unsigned long order, count, i;
+
+	order = get_order(size);
+	vaddr = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, order);
+	if (!vaddr)
+		return NULL;
+
+	count = 1 << order;
+	page = virt_to_page(vaddr);
+	for (i = 0; i < count; i++)
+		SetPageReserved(page + i);
+	return vaddr;
+}
+
+void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size)
+{
+	struct page *page;
+	unsigned long order, count, i;
+
+	order = get_order(size);
+	count = 1 << order;
+	page = virt_to_page(vaddr);
+	for (i = 0; i < count; i++)
+		ClearPageReserved(page + i);
+	__free_pages(page, order);
+}
+
+u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
+{
+	struct elf_prstatus prstatus;
+
+	memset(&prstatus, 0, sizeof(prstatus));
+	/*
+	 * FIXME: How do i get PID? Do I really need it?
+	 * prstatus.pr_pid = ????
+	 */
+	elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
+	buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
+			      &prstatus, sizeof(prstatus));
+	return buf;
+}
+
+void fadump_update_elfcore_header(struct fw_dump *fadump_conf, char *bufp)
+{
+	struct elfhdr *elf;
+	struct elf_phdr *phdr;
+
+	elf = (struct elfhdr *)bufp;
+	bufp += sizeof(struct elfhdr);
+
+	/* First note is a place holder for cpu notes info. */
+	phdr = (struct elf_phdr *)bufp;
+
+	if (phdr->p_type == PT_NOTE) {
+		phdr->p_paddr  = fadump_conf->cpu_notes_buf;
+		phdr->p_offset = phdr->p_paddr;
+		phdr->p_memsz  = fadump_conf->cpu_notes_buf_size;
+		phdr->p_filesz = phdr->p_memsz;
+	}
+}
+
+/*
+ * Returns 1, if there are no holes in memory area between d_start to d_end,
+ * 0 otherwise.
+ */
+static int is_fadump_memory_area_contiguous(unsigned long d_start,
+					    unsigned long d_end)
+{
+	struct memblock_region *reg;
+	unsigned long start, end;
+	int ret = 0;
+
+	for_each_memblock(memory, reg) {
+		start = max_t(unsigned long, d_start, reg->base);
+		end = min_t(unsigned long, d_end, (reg->base + reg->size));
+		if (d_start < end) {
+			/* Memory hole from d_start to start */
+			if (start > d_start)
+				break;
+
+			if (end == d_end) {
+				ret = 1;
+				break;
+			}
+
+			d_start = end + 1;
+		}
+	}
+
+	return ret;
+}
+
+/*
+ * Returns 1, if there are no holes in boot memory area,
+ * 0 otherwise.
+ */
+int is_fadump_boot_mem_contiguous(struct fw_dump *fadump_conf)
+{
+	unsigned long d_start = RMA_START;
+	unsigned long d_end   = RMA_START + fadump_conf->boot_memory_size;
+
+	return is_fadump_memory_area_contiguous(d_start, d_end);
+}
+
+/*
+ * Returns 1, if there are no holes in reserved memory area,
+ * 0 otherwise.
+ */
+int is_fadump_reserved_mem_contiguous(struct fw_dump *fadump_conf)
+{
+	unsigned long d_start = fadump_conf->reserve_dump_area_start;
+	unsigned long d_end   = d_start + fadump_conf->reserve_dump_area_size;
+
+	return is_fadump_memory_area_contiguous(d_start, d_end);
+}
diff --git a/arch/powerpc/kernel/fadump-common.h b/arch/powerpc/kernel/fadump-common.h
index e0673b2..54328ef 100644
--- a/arch/powerpc/kernel/fadump-common.h
+++ b/arch/powerpc/kernel/fadump-common.h
@@ -86,4 +86,12 @@ struct fw_dump {
 	unsigned long	nocma:1;
 };
 
+/* Helper functions */
+void *fadump_cpu_notes_buf_alloc(unsigned long size);
+void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size);
+u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs);
+void fadump_update_elfcore_header(struct fw_dump *fadump_config, char *bufp);
+int is_fadump_boot_mem_contiguous(struct fw_dump *fadump_conf);
+int is_fadump_reserved_mem_contiguous(struct fw_dump *fadump_conf);
+
 #endif /* __PPC64_FA_DUMP_INTERNAL_H__ */
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index e8630bb..40e5e96 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -37,9 +37,6 @@
 static struct fw_dump fw_dump;
 static struct fadump_mem_struct fdm;
 static const struct fadump_mem_struct *fdm_active;
-#ifdef CONFIG_CMA
-static struct cma *fadump_cma;
-#endif
 
 static DEFINE_MUTEX(fadump_mutex);
 struct fad_crash_memory_ranges *crash_memory_ranges;
@@ -48,6 +45,8 @@ int crash_mem_ranges;
 int max_crash_mem_ranges;
 
 #ifdef CONFIG_CMA
+static struct cma *fadump_cma;
+
 /*
  * fadump_cma_init() - Initialize CMA area from a fadump reserved memory
  *
@@ -109,8 +108,8 @@ static int __init fadump_cma_init(void) { return 1; }
 #endif /* CONFIG_CMA */
 
 /* Scan the Firmware Assisted dump configuration details. */
-int __init early_init_dt_scan_fw_dump(unsigned long node,
-			const char *uname, int depth, void *data)
+int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
+				      int depth, void *data)
 {
 	const __be32 *sections;
 	int i, num_sections;
@@ -201,67 +200,6 @@ int is_fadump_active(void)
 	return fw_dump.dump_active;
 }
 
-/*
- * Returns 1, if there are no holes in boot memory area,
- * 0 otherwise.
- */
-static int is_boot_memory_area_contiguous(void)
-{
-	struct memblock_region *reg;
-	unsigned long tstart, tend;
-	unsigned long start_pfn = PHYS_PFN(RMA_START);
-	unsigned long end_pfn = PHYS_PFN(RMA_START + fw_dump.boot_memory_size);
-	unsigned int ret = 0;
-
-	for_each_memblock(memory, reg) {
-		tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
-		tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
-		if (tstart < tend) {
-			/* Memory hole from start_pfn to tstart */
-			if (tstart > start_pfn)
-				break;
-
-			if (tend == end_pfn) {
-				ret = 1;
-				break;
-			}
-
-			start_pfn = tend + 1;
-		}
-	}
-
-	return ret;
-}
-
-/*
- * Returns true, if there are no holes in reserved memory area,
- * false otherwise.
- */
-static bool is_reserved_memory_area_contiguous(void)
-{
-	struct memblock_region *reg;
-	unsigned long start, end;
-	unsigned long d_start = fw_dump.reserve_dump_area_start;
-	unsigned long d_end = d_start + fw_dump.reserve_dump_area_size;
-
-	for_each_memblock(memory, reg) {
-		start = max(d_start, (unsigned long)reg->base);
-		end = min(d_end, (unsigned long)(reg->base + reg->size));
-		if (d_start < end) {
-			/* Memory hole from d_start to start */
-			if (start > d_start)
-				break;
-
-			if (end == d_end)
-				return true;
-
-			d_start = end + 1;
-		}
-	}
-
-	return false;
-}
-
 /* Print firmware assisted dump configurations for debugging purpose. */
 static void fadump_show_config(void)
 {
@@ -627,9 +565,9 @@ static int register_fw_dump(struct fadump_mem_struct *fdm)
 			" dump. Hardware Error(%d).\n", rc);
 		break;
 	case -3:
-		if (!is_boot_memory_area_contiguous())
+		if (!is_fadump_boot_mem_contiguous(&fw_dump))
 			pr_err("Can't have holes in boot memory area while registering fadump\n");
-		else if (!is_reserved_memory_area_contiguous())
+		else if (!is_fadump_reserved_mem_contiguous(&fw_dump))
 			pr_err("Can't have holes in reserved memory area while"
 			       " registering fadump\n");
 
@@ -759,72 +697,6 @@ fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
 	return reg_entry;
 }
 
-static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
-{
-	struct elf_prstatus prstatus;
-
-	memset(&prstatus, 0, sizeof(prstatus));
-	/*
-	 * FIXME: How do i get PID? Do I really need it?
-	 * prstatus.pr_pid = ????
-	 */
-	elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
-	buf = append_elf_note(buf, CRASH_CORE_NOTE_NAME, NT_PRSTATUS,
-			      &prstatus, sizeof(prstatus));
-	return buf;
-}
-
-static void fadump_update_elfcore_header(char *bufp)
-{
-	struct elfhdr *elf;
-	struct elf_phdr *phdr;
-
-	elf = (struct elfhdr *)bufp;
-	bufp += sizeof(struct elfhdr);
-
-	/* First note is a place holder for cpu notes info. */
-	phdr = (struct elf_phdr *)bufp;
-
-	if (phdr->p_type == PT_NOTE) {
-		phdr->p_paddr = fw_dump.cpu_notes_buf;
-		phdr->p_offset	= phdr->p_paddr;
-		phdr->p_filesz	= fw_dump.cpu_notes_buf_size;
-		phdr->p_memsz = fw_dump.cpu_notes_buf_size;
-	}
-	return;
-}
-
-static void *fadump_cpu_notes_buf_alloc(unsigned long size)
-{
-	void *vaddr;
-	struct page *page;
-	unsigned long order, count, i;
-
-	order = get_order(size);
-	vaddr = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, order);
-	if (!vaddr)
-		return NULL;
-
-	count = 1 << order;
-	page = virt_to_page(vaddr);
-	for (i = 0; i < count; i++)
-		SetPageReserved(page + i);
-	return vaddr;
-}
-
-static void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size)
-{
-	struct page *page;
-	unsigned long order, count, i;
-
-	order = get_order(size);
-	count = 1 << order;
-	page = virt_to_page(vaddr);
-	for (i = 0; i < count; i++)
-		ClearPageReserved(page + i);
-	__free_pages(page, order);
-}
-
 /*
  * Read CPU state dump data and convert it into ELF notes.
  * The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be
@@ -914,9 +786,9 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
 	final_note(note_buf);
 
 	if (fdh) {
-		pr_debug("Updating elfcore header (%llx) with cpu notes\n",
-							fdh->elfcorehdr_addr);
-		fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr));
+		addr = fdh->elfcorehdr_addr;
+		pr_debug("Updating elfcore header(%lx) with cpu notes\n", addr);
+		fadump_update_elfcore_header(&fw_dump, (char *)__va(addr));
 	}
 	return 0;
 


^ permalink raw reply related

* [PATCH v5 01/31] powerpc/fadump: move internal macros/definitions to a new header
From: Hari Bathini @ 2019-08-20 12:04 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: Ananth N Mavinakayanahalli, Mahesh J Salgaonkar, Vasant Hegde,
	Oliver, Nicholas Piggin, Daniel Axtens
In-Reply-To: <156630261682.8896.3418665808003586786.stgit@hbathini.in.ibm.com>

Though asm/fadump.h is meant to be used by other components dealing
with FADump, it also has macros/definitions internal to FADump code.
Move them to a new header file used within FADump code. This also
makes way for refactoring platform specific FADump code.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
 arch/powerpc/include/asm/fadump.h   |   71 ----------------------------
 arch/powerpc/kernel/fadump-common.h |   89 +++++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/fadump.c        |    2 +
 3 files changed, 91 insertions(+), 71 deletions(-)
 create mode 100644 arch/powerpc/kernel/fadump-common.h

diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 17d9b6a..75179497 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -11,34 +11,6 @@
 
 #ifdef CONFIG_FA_DUMP
 
-/*
- * The RMA region will be saved for later dumping when kernel crashes.
- * RMA is Real Mode Area, the first block of logical memory address owned
- * by logical partition, containing the storage that may be accessed with
- * translate off.
- */
-#define RMA_START	0x0
-#define RMA_END		(ppc64_rma_size)
-
-/*
- * On some Power systems where RMO is 128MB, it still requires minimum of
- * 256MB for kernel to boot successfully. When kdump infrastructure is
- * configured to save vmcore over network, we run into OOM issue while
- * loading modules related to network setup. Hence we need aditional 64M
- * of memory to avoid OOM issue.
- */
-#define MIN_BOOT_MEM	(((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \
-			+ (0x1UL << 26))
-
-/* The upper limit percentage for user specified boot memory size (25%) */
-#define MAX_BOOT_MEM_RATIO			4
-
-#define memblock_num_regions(memblock_type)	(memblock.memblock_type.cnt)
-
-/* Alignement per CMA requirement. */
-#define FADUMP_CMA_ALIGNMENT	(PAGE_SIZE <<				\
-			max_t(unsigned long, MAX_ORDER - 1, pageblock_order))
-
 /* Firmware provided dump sections */
 #define FADUMP_CPU_STATE_DATA	0x0001
 #define FADUMP_HPTE_REGION	0x0002
@@ -47,11 +19,6 @@
 /* Dump request flag */
 #define FADUMP_REQUEST_FLAG	0x00000001
 
-/* FAD commands */
-#define FADUMP_REGISTER		1
-#define FADUMP_UNREGISTER	2
-#define FADUMP_INVALIDATE	3
-
 /* Dump status flag */
 #define FADUMP_ERROR_FLAG	0x2000
 
@@ -112,29 +79,6 @@ struct fadump_mem_struct {
 	struct fadump_section		rmr_region;
 };
 
-/* Firmware-assisted dump configuration details. */
-struct fw_dump {
-	unsigned long	cpu_state_data_size;
-	unsigned long	hpte_region_size;
-	unsigned long	boot_memory_size;
-	unsigned long	reserve_dump_area_start;
-	unsigned long	reserve_dump_area_size;
-	/* cmd line option during boot */
-	unsigned long	reserve_bootvar;
-
-	unsigned long	fadumphdr_addr;
-	unsigned long	cpu_notes_buf;
-	unsigned long	cpu_notes_buf_size;
-
-	int		ibm_configure_kernel_dump;
-
-	unsigned long	fadump_enabled:1;
-	unsigned long	fadump_supported:1;
-	unsigned long	dump_active:1;
-	unsigned long	dump_registered:1;
-	unsigned long	nocma:1;
-};
-
 /*
  * Copy the ascii values for first 8 characters from a string into u64
  * variable at their respective indexes.
@@ -153,7 +97,6 @@ static inline u64 str_to_u64(const char *str)
 #define STR_TO_HEX(x)	str_to_u64(x)
 #define REG_ID(x)	str_to_u64(x)
 
-#define FADUMP_CRASH_INFO_MAGIC		STR_TO_HEX("FADMPINF")
 #define REGSAVE_AREA_MAGIC		STR_TO_HEX("REGSAVE")
 
 /* The firmware-assisted dump format.
@@ -178,20 +121,6 @@ struct fadump_reg_entry {
 	__be64		reg_value;
 };
 
-/* fadump crash info structure */
-struct fadump_crash_info_header {
-	u64		magic_number;
-	u64		elfcorehdr_addr;
-	u32		crashing_cpu;
-	struct pt_regs	regs;
-	struct cpumask	online_mask;
-};
-
-struct fad_crash_memory_ranges {
-	unsigned long long	base;
-	unsigned long long	size;
-};
-
 extern int is_fadump_memory_area(u64 addr, ulong size);
 extern int early_init_dt_scan_fw_dump(unsigned long node,
 		const char *uname, int depth, void *data);
diff --git a/arch/powerpc/kernel/fadump-common.h b/arch/powerpc/kernel/fadump-common.h
new file mode 100644
index 0000000..e0673b2
--- /dev/null
+++ b/arch/powerpc/kernel/fadump-common.h
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Firmware-Assisted Dump internal code.
+ *
+ * Copyright 2011, IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.ibm.com>
+ *
+ * Copyright 2019, IBM Corp.
+ * Author: Hari Bathini <hbathini@linux.ibm.com>
+ */
+
+#ifndef __PPC64_FA_DUMP_INTERNAL_H__
+#define __PPC64_FA_DUMP_INTERNAL_H__
+
+/*
+ * The RMA region will be saved for later dumping when kernel crashes.
+ * RMA is Real Mode Area, the first block of logical memory address owned
+ * by logical partition, containing the storage that may be accessed with
+ * translate off.
+ */
+#define RMA_START	0x0
+#define RMA_END		(ppc64_rma_size)
+
+/*
+ * On some Power systems where RMO is 128MB, it still requires minimum of
+ * 256MB for kernel to boot successfully. When kdump infrastructure is
+ * configured to save vmcore over network, we run into OOM issue while
+ * loading modules related to network setup. Hence we need additional 64M
+ * of memory to avoid OOM issue.
+ */
+#define MIN_BOOT_MEM	(((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \
+			+ (0x1UL << 26))
+
+/* The upper limit percentage for user specified boot memory size (25%) */
+#define MAX_BOOT_MEM_RATIO			4
+
+#define memblock_num_regions(memblock_type)	(memblock.memblock_type.cnt)
+
+/* Alignment per CMA requirement. */
+#define FADUMP_CMA_ALIGNMENT	(PAGE_SIZE <<				\
+				 max_t(unsigned long, MAX_ORDER - 1,	\
+				 pageblock_order))
+
+/* FAD commands */
+#define FADUMP_REGISTER			1
+#define FADUMP_UNREGISTER		2
+#define FADUMP_INVALIDATE		3
+
+#define FADUMP_CRASH_INFO_MAGIC		str_to_u64("FADMPINF")
+
+/* fadump crash info structure */
+struct fadump_crash_info_header {
+	u64		magic_number;
+	u64		elfcorehdr_addr;
+	u32		crashing_cpu;
+	struct pt_regs	regs;
+	struct cpumask	online_mask;
+};
+
+struct fad_crash_memory_ranges {
+	unsigned long long	base;
+	unsigned long long	size;
+};
+
+/* Firmware-assisted dump configuration details. */
+struct fw_dump {
+	unsigned long	reserve_dump_area_start;
+	unsigned long	reserve_dump_area_size;
+	/* cmd line option during boot */
+	unsigned long	reserve_bootvar;
+
+	unsigned long	cpu_state_data_size;
+	unsigned long	hpte_region_size;
+	unsigned long	boot_memory_size;
+
+	unsigned long	fadumphdr_addr;
+	unsigned long	cpu_notes_buf;
+	unsigned long	cpu_notes_buf_size;
+
+	int		ibm_configure_kernel_dump;
+
+	unsigned long	fadump_enabled:1;
+	unsigned long	fadump_supported:1;
+	unsigned long	dump_active:1;
+	unsigned long	dump_registered:1;
+	unsigned long	nocma:1;
+};
+
+#endif /* __PPC64_FA_DUMP_INTERNAL_H__ */
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 4eab972..e8630bb 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -32,6 +32,8 @@
 #include <asm/fadump.h>
 #include <asm/setup.h>
 
+#include "fadump-common.h"
+
 static struct fw_dump fw_dump;
 static struct fadump_mem_struct fdm;
 static const struct fadump_mem_struct *fdm_active;


^ permalink raw reply related

* [PATCH v5 00/31] Add FADump support on PowerNV platform
From: Hari Bathini @ 2019-08-20 12:04 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: Ananth N Mavinakayanahalli, Mahesh J Salgaonkar, Vasant Hegde,
	Oliver, Nicholas Piggin, Daniel Axtens

Firmware-Assisted Dump (FADump) is currently supported only on pSeries
platform. This patch series adds support for PowerNV platform too.

The first few patches refactor the FADump code to make use of common
code across multiple platforms. Then basic FADump support is added for
PowerNV platform. Followed by patches to honour reserved-ranges DT node
while reserving/releasing memory used by FADump. The subsequent patch
processes CPU state data provided by firmware to create and append core
notes to the ELF core file and the next patch adds support to preserve
crash data for subsequent boots (useful in cases like petitboot). The
subsequent patches add support to export opalcore. opalcore makes
debugging of failures in OPAL code easier. Firmware-Assisted Dump
documentation is also updated appropriately.

The patch series is tested with the latest firmware plus the below skiboot
changes, accepted upstream recently, for MPIPL support:

    https://patchwork.ozlabs.org/project/skiboot/list/?series=119169
    ("MPIPL support")


Changes in v5:
  * Split the patches further.
  * Rebased to latest upstream kernel version.
  * Updated the patches based on discussions with mahesh on V4.

---

Hari Bathini (31):
      powerpc/fadump: move internal macros/definitions to a new header
      powerpc/fadump: move internal code to a new file
      powerpc/fadump: Improve fadump documentation
      pseries/fadump: move rtas specific definitions to platform code
      pseries/fadump: introduce callbacks for platform specific operations
      pseries/fadump: define register/un-register callback functions
      powerpc/fadump: release all the memory above boot memory size
      pseries/fadump: move out platform specific support from generic code
      powerpc/fadump: use FADump instead of fadump for how it is pronounced
      opal: add MPIPL interface definitions
      powernv/fadump: add fadump support on powernv
      powernv/fadump: register kernel metadata address with opal
      powernv/fadump: reset metadata address during clean up
      powernv/fadump: define register/un-register callback functions
      powernv/fadump: support copying multiple kernel boot memory regions
      powernv/fadump: process the crashdump by exporting it as /proc/vmcore
      powernv/fadump: Warn before processing partial crashdump
      powernv/fadump: handle invalidation of crashdump and re-registraion
      powerpc/fadump: Update documentation about OPAL platform support
      powerpc/fadump: use smaller offset while finding memory for reservation
      powernv/fadump: process architected register state data provided by firmware
      powerpc/fadump: make crash memory ranges array allocation generic
      powerpc/fadump: consider reserved ranges while releasing memory
      powerpc/fadump: improve how crashed kernel's memory is reserved
      powernv/fadump: add support to preserve crash data on FADUMP disabled kernel
      powerpc/fadump: update documentation about CONFIG_PRESERVE_FA_DUMP
      powernv/opalcore: export /sys/firmware/opal/core for analysing opal crashes
      powernv/opalcore: provide an option to invalidate /sys/firmware/opal/core file
      powerpc/fadump: consider f/w load area
      powernv/fadump: update documentation about option to release opalcore
      powernv/fadump: support holes in kernel boot memory area


 Documentation/powerpc/firmware-assisted-dump.rst |  204 ++--
 arch/powerpc/Kconfig                             |   23 
 arch/powerpc/include/asm/fadump.h                |  190 ---
 arch/powerpc/include/asm/opal-api.h              |   50 +
 arch/powerpc/include/asm/opal.h                  |    6 
 arch/powerpc/kernel/Makefile                     |    6 
 arch/powerpc/kernel/fadump-common.c              |  149 +++
 arch/powerpc/kernel/fadump-common.h              |  192 +++
 arch/powerpc/kernel/fadump.c                     | 1272 ++++++++--------------
 arch/powerpc/kernel/prom.c                       |    4 
 arch/powerpc/platforms/powernv/Makefile          |    3 
 arch/powerpc/platforms/powernv/opal-call.c       |    3 
 arch/powerpc/platforms/powernv/opal-core.c       |  633 +++++++++++
 arch/powerpc/platforms/powernv/opal-fadump.c     |  715 ++++++++++++
 arch/powerpc/platforms/powernv/opal-fadump.h     |  148 +++
 arch/powerpc/platforms/pseries/Makefile          |    1 
 arch/powerpc/platforms/pseries/rtas-fadump.c     |  593 ++++++++++
 arch/powerpc/platforms/pseries/rtas-fadump.h     |  117 ++
 18 files changed, 3267 insertions(+), 1042 deletions(-)
 create mode 100644 arch/powerpc/kernel/fadump-common.c
 create mode 100644 arch/powerpc/kernel/fadump-common.h
 create mode 100644 arch/powerpc/platforms/powernv/opal-core.c
 create mode 100644 arch/powerpc/platforms/powernv/opal-fadump.c
 create mode 100644 arch/powerpc/platforms/powernv/opal-fadump.h
 create mode 100644 arch/powerpc/platforms/pseries/rtas-fadump.c
 create mode 100644 arch/powerpc/platforms/pseries/rtas-fadump.h


^ permalink raw reply

* [PATCH RESEND v11 8/8] selftests: add openat2(2) selftests
From: Aleksa Sarai @ 2019-08-20  3:34 UTC (permalink / raw)
  To: Al Viro, Jeff Layton, J. Bruce Fields, Arnd Bergmann,
	David Howells, Shuah Khan, Shuah Khan
  Cc: linux-ia64, linux-sh, Alexei Starovoitov, Oleg Nesterov,
	linux-kselftest, sparclinux, linux-arch, linux-s390,
	Tycho Andersen, Aleksa Sarai, linux-arm-kernel, linux-mips,
	linux-xtensa, Kees Cook, Jann Horn, linuxppc-dev, Aleksa Sarai,
	Andy Lutomirski, David Drysdale, Christian Brauner, linux-parisc,
	linux-m68k, linux-api, Chanho Min, linux-kernel, Eric Biederman,
	linux-alpha, linux-fsdevel, Andrew Morton, Linus Torvalds,
	containers
In-Reply-To: <20190820033406.29796-1-cyphar@cyphar.com>

Test all of the various openat2(2) flags, as well as how file
descriptor re-opening works. A small stress-test of a symlink-rename
attack is included to show that the protections against ".."-based
attacks are sufficient.

In addition, the memfd selftest is fixed to no longer depend on the
now-disallowed functionality of upgrading an O_RDONLY descriptor to
O_RDWR.

Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
---
 tools/testing/selftests/Makefile              |   1 +
 tools/testing/selftests/memfd/memfd_test.c    |   7 +-
 tools/testing/selftests/openat2/.gitignore    |   1 +
 tools/testing/selftests/openat2/Makefile      |   8 +
 tools/testing/selftests/openat2/helpers.c     | 162 +++++++
 tools/testing/selftests/openat2/helpers.h     | 116 +++++
 .../testing/selftests/openat2/linkmode_test.c | 333 +++++++++++++++
 .../selftests/openat2/rename_attack_test.c    | 127 ++++++
 .../testing/selftests/openat2/resolve_test.c  | 402 ++++++++++++++++++
 9 files changed, 1155 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/openat2/.gitignore
 create mode 100644 tools/testing/selftests/openat2/Makefile
 create mode 100644 tools/testing/selftests/openat2/helpers.c
 create mode 100644 tools/testing/selftests/openat2/helpers.h
 create mode 100644 tools/testing/selftests/openat2/linkmode_test.c
 create mode 100644 tools/testing/selftests/openat2/rename_attack_test.c
 create mode 100644 tools/testing/selftests/openat2/resolve_test.c

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 25b43a8c2b15..13c02e0d0efc 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -37,6 +37,7 @@ TARGETS += powerpc
 TARGETS += proc
 TARGETS += pstore
 TARGETS += ptrace
+TARGETS += openat2
 TARGETS += rseq
 TARGETS += rtc
 TARGETS += seccomp
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index c67d32eeb668..e71df3d3e55d 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -925,7 +925,7 @@ static void test_share_mmap(char *banner, char *b_suffix)
  */
 static void test_share_open(char *banner, char *b_suffix)
 {
-	int fd, fd2;
+	int procfd, fd, fd2;
 
 	printf("%s %s %s\n", memfd_str, banner, b_suffix);
 
@@ -950,13 +950,16 @@ static void test_share_open(char *banner, char *b_suffix)
 	mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK);
 	mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK);
 
+	/* We cannot do a MAY_WRITE re-open of an O_RDONLY fd. */
+	procfd = mfd_assert_open(fd2, O_PATH, 0);
 	close(fd2);
-	fd2 = mfd_assert_open(fd, O_RDWR, 0);
+	fd2 = mfd_assert_open(procfd, O_WRONLY, 0);
 
 	mfd_assert_add_seals(fd2, F_SEAL_SEAL);
 	mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL);
 	mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL);
 
+	close(procfd);
 	close(fd2);
 	close(fd);
 }
diff --git a/tools/testing/selftests/openat2/.gitignore b/tools/testing/selftests/openat2/.gitignore
new file mode 100644
index 000000000000..bd68f6c3fd07
--- /dev/null
+++ b/tools/testing/selftests/openat2/.gitignore
@@ -0,0 +1 @@
+/*_test
diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile
new file mode 100644
index 000000000000..a0c1b53fd268
--- /dev/null
+++ b/tools/testing/selftests/openat2/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+
+CFLAGS += -Wall -O2 -g
+TEST_GEN_PROGS := linkmode_test resolve_test rename_attack_test
+
+include ../lib.mk
+
+$(TEST_GEN_PROGS): helpers.c
diff --git a/tools/testing/selftests/openat2/helpers.c b/tools/testing/selftests/openat2/helpers.c
new file mode 100644
index 000000000000..b9b7c7fc7a99
--- /dev/null
+++ b/tools/testing/selftests/openat2/helpers.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Author: Aleksa Sarai <cyphar@cyphar.com>
+ * Copyright (C) 2018-2019 SUSE LLC.
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <stdbool.h>
+#include <string.h>
+#include <syscall.h>
+#include <limits.h>
+
+#include "helpers.h"
+
+int sys_openat2(int dfd, const char *path, const struct open_how *how)
+{
+	int ret = syscall(__NR_openat2, dfd, path, how);
+	return ret >= 0 ? ret : -errno;
+}
+
+int sys_openat(int dfd, const char *path, const struct open_how *how)
+{
+	int ret = openat(dfd, path, how->flags, how->mode);
+	return ret >= 0 ? ret : -errno;
+}
+
+int sys_renameat2(int olddirfd, const char *oldpath,
+		  int newdirfd, const char *newpath, unsigned int flags)
+{
+	int ret = syscall(__NR_renameat2, olddirfd, oldpath,
+					  newdirfd, newpath, flags);
+	return ret >= 0 ? ret : -errno;
+}
+
+char *openat_flags(unsigned int flags)
+{
+	char *flagset, *accmode = "(none)";
+
+	switch (flags & 0x03) {
+	case O_RDWR:
+		accmode = "O_RDWR";
+		break;
+	case O_RDONLY:
+		accmode = "O_RDONLY";
+		break;
+	case O_WRONLY:
+		accmode = "O_WRONLY";
+		break;
+	}
+
+	E_asprintf(&flagset, "%s%s%s",
+		   (flags & O_PATH) ? "O_PATH|" : "",
+		   (flags & O_CREAT) ? "O_CREAT|" : "",
+		   accmode);
+
+	return flagset;
+}
+
+char *openat2_flags(const struct open_how *how)
+{
+	char *p;
+	char *flags_set, *resolve_set, *acc_set, *set;
+
+	flags_set = openat_flags(how->flags);
+
+	E_asprintf(&resolve_set, "%s%s%s%s%s0",
+		   (how->resolve & RESOLVE_NO_XDEV) ? "RESOLVE_NO_XDEV|" : "",
+		   (how->resolve & RESOLVE_NO_MAGICLINKS) ? "RESOLVE_NO_MAGICLINKS|" : "",
+		   (how->resolve & RESOLVE_NO_SYMLINKS) ? "RESOLVE_NO_SYMLINKS|" : "",
+		   (how->resolve & RESOLVE_BENEATH) ? "RESOLVE_BENEATH|" : "",
+		   (how->resolve & RESOLVE_IN_ROOT) ? "RESOLVE_IN_ROOT|" : "");
+
+	/* Remove trailing "|0". */
+	p = strstr(resolve_set, "|0");
+	if (p)
+		*p = '\0';
+
+	if (how->flags & O_PATH)
+		E_asprintf(&acc_set, ", upgrade_mask=%s%s0",
+			   (how->upgrade_mask & UPGRADE_NOREAD) ? "UPGRADE_NOREAD|" : "",
+			   (how->upgrade_mask & UPGRADE_NOWRITE) ? "UPGRADE_NOWRITE|" : "");
+	else if (how->flags & O_CREAT)
+		E_asprintf(&acc_set, ", mode=0%o", how->mode);
+	else
+		acc_set = strdup("");
+
+	/* Remove trailing "|0". */
+	p = strstr(acc_set, "|0");
+	if (p)
+		*p = '\0';
+
+	/* And now generate our flagset. */
+	E_asprintf(&set, "[flags=%s, resolve=%s%s]",
+		   flags_set, resolve_set, acc_set);
+
+	free(flags_set);
+	free(resolve_set);
+	free(acc_set);
+	return set;
+}
+
+int touchat(int dfd, const char *path)
+{
+	int fd = openat(dfd, path, O_CREAT);
+	if (fd >= 0)
+		close(fd);
+	return fd;
+}
+
+char *fdreadlink(int fd)
+{
+	char *target, *tmp;
+
+	E_asprintf(&tmp, "/proc/self/fd/%d", fd);
+
+	target = malloc(PATH_MAX);
+	if (!target)
+		ksft_exit_fail_msg("fdreadlink: malloc failed\n");
+	memset(target, 0, PATH_MAX);
+
+	E_readlink(tmp, target, PATH_MAX);
+	free(tmp);
+	return target;
+}
+
+bool fdequal(int fd, int dfd, const char *path)
+{
+	char *fdpath, *dfdpath, *other;
+	bool cmp;
+
+	fdpath = fdreadlink(fd);
+	dfdpath = fdreadlink(dfd);
+
+	if (!path)
+		E_asprintf(&other, "%s", dfdpath);
+	else if (*path == '/')
+		E_asprintf(&other, "%s", path);
+	else
+		E_asprintf(&other, "%s/%s", dfdpath, path);
+
+	cmp = !strcmp(fdpath, other);
+	if (!cmp)
+		ksft_print_msg("fdequal: expected '%s' but got '%s'\n", other, fdpath);
+
+	free(fdpath);
+	free(dfdpath);
+	free(other);
+	return cmp;
+}
+
+void test_openat2_supported(void)
+{
+	struct open_how how = {};
+	int fd = sys_openat2(AT_FDCWD, ".", &how);
+	if (fd == -ENOSYS)
+		ksft_exit_skip("openat2(2) unsupported on this kernel\n");
+	if (fd < 0)
+		ksft_exit_fail_msg("openat2(2) supported check failed: %s\n", strerror(-fd));
+	close(fd);
+}
diff --git a/tools/testing/selftests/openat2/helpers.h b/tools/testing/selftests/openat2/helpers.h
new file mode 100644
index 000000000000..43fa7835950f
--- /dev/null
+++ b/tools/testing/selftests/openat2/helpers.h
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Author: Aleksa Sarai <cyphar@cyphar.com>
+ * Copyright (C) 2018-2019 SUSE LLC.
+ */
+
+#ifndef __RESOLVEAT_H__
+#define __RESOLVEAT_H__
+
+#define _GNU_SOURCE
+#include <stdint.h>
+#include <errno.h>
+#include "../kselftest.h"
+
+#define ARRAY_LEN(X) (sizeof (X) / sizeof (*(X)))
+#define BUILD_BUG_ON(e) ((void)(sizeof(struct { int:(-!!(e)); })))
+
+#ifndef SYS_openat2
+#ifndef __NR_openat2
+#define __NR_openat2 437
+#endif /* __NR_openat2 */
+#define SYS_openat2 __NR_openat2
+#endif /* SYS_openat2 */
+
+/**
+ * Arguments for how openat2(2) should open the target path. If @extra is zero,
+ * then openat2 is identical to openat(2). Only one of @mode or @upgrade_mask
+ * may be set at any given time.
+ *
+ * @flags: O_* flags (unknown flags ignored).
+ * @mode: O_CREAT file mode (ignored otherwise).
+ * @upgrade_mask: restrict how the O_PATH may be re-opened (ignored otherwise).
+ * @resolve: RESOLVE_* flags (-EINVAL on unknown flags).
+ * @reserved: reserved for future extensions, must be zeroed.
+ */
+struct open_how {
+	uint32_t flags;
+	union {
+		uint16_t mode;
+		uint16_t upgrade_mask;
+	};
+	uint16_t resolve;
+	uint64_t reserved[7]; /* must be zeroed */
+};
+
+#ifndef RESOLVE_INROOT
+/* how->resolve flags for openat2(2). */
+#define RESOLVE_NO_XDEV		0x01 /* Block mount-point crossings
+					(includes bind-mounts). */
+#define RESOLVE_NO_MAGICLINKS	0x02 /* Block traversal through procfs-style
+					"magic-links". */
+#define RESOLVE_NO_SYMLINKS	0x04 /* Block traversal through all symlinks
+					(implies OEXT_NO_MAGICLINKS) */
+#define RESOLVE_BENEATH		0x08 /* Block "lexical" trickery like
+					"..", symlinks, and absolute
+					paths which escape the dirfd. */
+#define RESOLVE_IN_ROOT		0x10 /* Make all jumps to "/" and ".."
+					be scoped inside the dirfd
+					(similar to chroot(2)). */
+#endif /* RESOLVE_IN_ROOT */
+
+#ifndef UPGRADE_NOREAD
+/* how->upgrade flags for openat2(2). */
+/* First bit is reserved for a future UPGRADE_NOEXEC flag. */
+#define UPGRADE_NOREAD		0x02 /* Block re-opening with MAY_READ. */
+#define UPGRADE_NOWRITE		0x04 /* Block re-opening with MAY_WRITE. */
+#endif /* UPGRADE_NOREAD */
+
+#ifndef O_EMPTYPATH
+#define	O_EMPTYPATH 040000000
+#endif /* O_EMPTYPATH */
+
+#define E_func(func, ...)						\
+	do {								\
+		if (func(__VA_ARGS__) < 0)				\
+			ksft_exit_fail_msg("%s:%d %s failed\n", \
+					   __FILE__, __LINE__, #func);\
+	} while (0)
+
+#define E_mkdirat(...)   E_func(mkdirat,   __VA_ARGS__)
+#define E_symlinkat(...) E_func(symlinkat, __VA_ARGS__)
+#define E_touchat(...)   E_func(touchat,   __VA_ARGS__)
+#define E_readlink(...)  E_func(readlink,  __VA_ARGS__)
+#define E_fstatat(...)   E_func(fstatat,   __VA_ARGS__)
+#define E_asprintf(...)  E_func(asprintf,  __VA_ARGS__)
+#define E_fchdir(...)    E_func(fchdir,    __VA_ARGS__)
+#define E_mount(...)     E_func(mount,     __VA_ARGS__)
+#define E_unshare(...)   E_func(unshare,   __VA_ARGS__)
+#define E_setresuid(...) E_func(setresuid, __VA_ARGS__)
+#define E_chmod(...)     E_func(chmod,     __VA_ARGS__)
+
+#define E_assert(expr, msg, ...)					\
+	do {								\
+		if (!(expr))						\
+			ksft_exit_fail_msg("ASSERT(%s:%d) failed (%s): " msg "\n", \
+					   __FILE__, __LINE__, #expr, ##__VA_ARGS__); \
+	} while (0)
+
+typedef int (*openfunc_t)(int dfd, const char *path, const struct open_how *how);
+
+int sys_openat2(int dfd, const char *path, const struct open_how *how);
+char *openat2_flags(const struct open_how *how);
+
+int sys_openat(int dfd, const char *path, const struct open_how *how);
+char *openat_flags(unsigned int flags);
+
+int sys_renameat2(int olddirfd, const char *oldpath,
+		  int newdirfd, const char *newpath, unsigned int flags);
+
+int touchat(int dfd, const char *path);
+char *fdreadlink(int fd);
+bool fdequal(int fd, int dfd, const char *path);
+
+void test_openat2_supported(void);
+
+#endif /* __RESOLVEAT_H__ */
diff --git a/tools/testing/selftests/openat2/linkmode_test.c b/tools/testing/selftests/openat2/linkmode_test.c
new file mode 100644
index 000000000000..44fcba738686
--- /dev/null
+++ b/tools/testing/selftests/openat2/linkmode_test.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Author: Aleksa Sarai <cyphar@cyphar.com>
+ * Copyright (C) 2018-2019 SUSE LLC.
+ */
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <stdbool.h>
+#include <string.h>
+
+#include "../kselftest.h"
+#include "helpers.h"
+
+static mode_t fdmode(int fd)
+{
+	char *fdpath;
+	struct stat statbuf;
+	mode_t mode;
+
+	E_asprintf(&fdpath, "/proc/self/fd/%d", fd);
+	E_fstatat(AT_FDCWD, fdpath, &statbuf, AT_SYMLINK_NOFOLLOW);
+	mode = (statbuf.st_mode & ~S_IFMT);
+	free(fdpath);
+
+	return mode;
+}
+
+static int reopen_proc(int fd, unsigned int flags)
+{
+	int ret, saved_errno;
+	char *fdpath;
+
+	E_asprintf(&fdpath, "/proc/self/fd/%d", fd);
+	ret = open(fdpath, flags);
+	saved_errno = errno;
+	free(fdpath);
+
+	return ret >= 0 ? ret : -saved_errno;
+}
+
+static int reopen_oemptypath(int fd, unsigned int flags)
+{
+	int ret = openat(fd, "", O_EMPTYPATH | flags);
+	return ret >= 0 ? ret : -errno;
+}
+
+struct reopen_test {
+	openfunc_t open;
+	mode_t chmod_mode;
+	struct {
+		struct open_how how;
+		mode_t mode;
+		int err;
+	} orig, new;
+};
+
+static bool reopen(int fd, struct reopen_test *test)
+{
+	int newfd;
+	mode_t proc_mode;
+	bool failed = false;
+
+	/* Check that the proc mode is correct. */
+	proc_mode = fdmode(fd);
+	if (proc_mode != test->orig.mode) {
+		ksft_print_msg("incorrect fdmode (got[%o] != want[%o])\n",
+			       proc_mode, test->orig.mode);
+		failed = true;
+	}
+
+	/* Re-open through /proc. */
+	newfd = reopen_proc(fd, test->new.how.flags);
+	if (newfd != test->new.err && (newfd < 0 || test->new.err < 0)) {
+		ksft_print_msg("/proc failure (%d != %d [%s])\n",
+			       newfd, test->new.err, strerror(-test->new.err));
+		failed = true;
+	}
+	if (newfd >= 0) {
+		proc_mode = fdmode(newfd);
+		if (proc_mode != test->new.mode) {
+			ksft_print_msg("/proc wrong fdmode (got[%o] != want[%o])\n",
+				       proc_mode, test->new.mode);
+			failed = true;
+		}
+		close(newfd);
+	}
+
+	/* Re-open with O_EMPTYPATH. */
+	newfd = reopen_oemptypath(fd, test->new.how.flags);
+	if (newfd != test->new.err && (newfd < 0 || test->new.err < 0)) {
+		ksft_print_msg("O_EMPTYPATH failure (%d != %d [%s])\n",
+			       newfd, test->new.err, strerror(-test->new.err));
+		failed = true;
+	}
+	if (newfd >= 0) {
+		proc_mode = fdmode(newfd);
+		if (proc_mode != test->new.mode) {
+			ksft_print_msg("O_EMPTYPATH wrong fdmode (got[%o] != want[%o])\n",
+				       proc_mode, test->new.mode);
+			failed = true;
+		}
+		close(newfd);
+	}
+
+	return failed;
+}
+
+#define NUM_REOPEN_TESTS 28
+
+void test_reopen_ordinary(bool privileged)
+{
+	int fd;
+	int err_access = privileged ? 0 : -EACCES;
+	char tmpfile[] = "/tmp/ksft-openat2-reopen-testfile.XXXXXX";
+
+	fd = mkstemp(tmpfile);
+	E_assert(fd >= 0, "mkstemp failed: %m\n");
+	close(fd);
+
+	struct reopen_test tests[] = {
+		/* Re-opening with the same mode should succeed. */
+		{ .open = sys_openat,	  .chmod_mode = 0400,
+		  .orig.how.flags = O_RDONLY, .orig.mode  = 0500,
+		  .new.how.flags  = O_RDONLY, .new.mode   = 0500 },
+		{ .open = sys_openat,	  .chmod_mode = 0200,
+		  .orig.how.flags = O_WRONLY, .orig.mode  = 0300,
+		  .new.how.flags  = O_WRONLY, .new.mode   = 0300 },
+		{ .open = sys_openat,	  .chmod_mode = 0600,
+		  .orig.how.flags =   O_RDWR, .orig.mode  = 0700,
+		  .new.how.flags  =   O_RDWR, .new.mode   = 0700 },
+		{ .open = sys_openat,	  .chmod_mode = 0600,
+		  .orig.how.flags =   O_RDWR, .orig.mode  = 0700,
+		  .new.how.flags  = O_RDONLY, .new.mode   = 0500 },
+		{ .open = sys_openat,	  .chmod_mode = 0600,
+		  .orig.how.flags =   O_RDWR, .orig.mode  = 0700,
+		  .new.how.flags  = O_WRONLY, .new.mode   = 0300 },
+
+		/*
+		 * Re-opening with a different mode will always fail (with an obvious
+		 * carve-out for privileged users).
+		 */
+		{ .open = sys_openat,	  .chmod_mode = 0600,
+		  .orig.how.flags = O_RDONLY, .orig.mode  = 0500,
+		  .new.how.flags  = O_WRONLY, .new.mode   = 0300, .new.err = err_access },
+		{ .open = sys_openat,	  .chmod_mode = 0600,
+		  .orig.how.flags = O_WRONLY, .orig.mode  = 0300,
+		  .new.how.flags  = O_RDONLY, .new.mode   = 0500, .new.err = err_access },
+		{ .open = sys_openat,	  .chmod_mode = 0600,
+		  .orig.how.flags = O_RDONLY, .orig.mode  = 0500,
+		  .new.how.flags  =   O_RDWR, .new.mode   = 0700, .new.err = err_access },
+		{ .open = sys_openat,	  .chmod_mode = 0600,
+		  .orig.how.flags = O_WRONLY, .orig.mode  = 0300,
+		  .new.how.flags  =   O_RDWR, .new.mode   = 0700, .new.err = err_access },
+
+		/* Doubly so if they didn't even have permissions at open-time. */
+		{ .open = sys_openat,	  .chmod_mode = 0400,
+		  .orig.how.flags = O_RDONLY, .orig.mode  = 0500,
+		  .new.how.flags  = O_WRONLY, .new.mode   = 0300, .new.err = err_access },
+		{ .open = sys_openat,	  .chmod_mode = 0200,
+		  .orig.how.flags = O_WRONLY, .orig.mode  = 0300,
+		  .new.how.flags  = O_RDONLY, .new.mode   = 0500, .new.err = err_access },
+		{ .open = sys_openat,	  .chmod_mode = 0400,
+		  .orig.how.flags = O_RDONLY, .orig.mode  = 0500,
+		  .new.how.flags  =   O_RDWR, .new.mode   = 0700, .new.err = err_access },
+		{ .open = sys_openat,	  .chmod_mode = 0200,
+		  .orig.how.flags = O_WRONLY, .orig.mode  = 0300,
+		  .new.how.flags  =   O_RDWR, .new.mode   = 0700, .new.err = err_access },
+
+		/* O_PATH re-opens (of ordinary files) will always work. */
+		{ .open = sys_openat,	  .chmod_mode = 0000,
+		  .orig.how.flags =   O_PATH, .orig.mode  = 0070,
+		  .new.how.flags  = O_WRONLY, .new.mode   = 0300 },
+		{ .open = sys_openat2,  .chmod_mode = 0000,
+		  .orig.how.flags =   O_PATH, .orig.mode  = 0070,
+		  .new.how.flags  = O_WRONLY, .new.mode   = 0300 },
+
+		{ .open = sys_openat,	  .chmod_mode = 0000,
+		  .orig.how.flags =   O_PATH, .orig.mode  = 0070,
+		  .new.how.flags  = O_RDONLY, .new.mode   = 0500 },
+		{ .open = sys_openat2,  .chmod_mode = 0000,
+		  .orig.how.flags =   O_PATH, .orig.mode  = 0070,
+		  .new.how.flags  = O_RDONLY, .new.mode   = 0500 },
+
+		{ .open = sys_openat,	  .chmod_mode = 0000,
+		  .orig.how.flags =   O_PATH, .orig.mode  = 0070,
+		  .new.how.flags  =   O_RDWR, .new.mode   = 0700 },
+		{ .open = sys_openat2,  .chmod_mode = 0000,
+		  .orig.how.flags =   O_PATH, .orig.mode  = 0070,
+		  .new.how.flags  =   O_RDWR, .new.mode   = 0700 },
+
+		/*
+		 * openat2(2) UPGRADE_NO* flags. In the privileged case, the re-open
+		 * will work but the mode will still be scoped to the mode (or'd with
+		 * the open acc_mode).
+		 */
+		{ .open = sys_openat2,  .chmod_mode = 0000,
+		  .orig.how.flags = O_PATH, .orig.mode = 0010,
+		  .orig.how.upgrade_mask = UPGRADE_NOREAD | UPGRADE_NOWRITE,
+		  .new.how.flags  = O_RDONLY, .new.mode   = 0500, .new.err = err_access },
+		{ .open = sys_openat2,  .chmod_mode = 0000,
+		  .orig.how.flags = O_PATH, .orig.mode = 0010,
+		  .orig.how.upgrade_mask = UPGRADE_NOREAD | UPGRADE_NOWRITE,
+		  .new.how.flags  = O_WRONLY, .new.mode   = 0300, .new.err = err_access },
+		{ .open = sys_openat2,  .chmod_mode = 0000,
+		  .orig.how.flags = O_PATH, .orig.mode = 0010,
+		  .orig.how.upgrade_mask = UPGRADE_NOREAD | UPGRADE_NOWRITE,
+		  .new.how.flags  =   O_RDWR, .new.mode   = 0700, .new.err = err_access },
+
+		{ .open = sys_openat2,  .chmod_mode = 0000,
+		  .orig.how.flags = O_PATH, .orig.mode = 0050,
+		  .orig.how.upgrade_mask = UPGRADE_NOWRITE,
+		  .new.how.flags  = O_RDONLY, .new.mode   = 0500 },
+
+		{ .open = sys_openat2,  .chmod_mode = 0000,
+		  .orig.how.flags = O_PATH, .orig.mode = 0030,
+		  .orig.how.upgrade_mask = UPGRADE_NOREAD,
+		  .new.how.flags  = O_WRONLY, .new.mode   = 0300 },
+
+		{ .open = sys_openat2,  .chmod_mode = 0000,
+		  .orig.how.flags = O_PATH, .orig.mode = 0030,
+		  .orig.how.upgrade_mask = UPGRADE_NOREAD,
+		  .new.how.flags  = O_RDONLY, .new.mode   = 0500, .new.err = err_access },
+		{ .open = sys_openat2,  .chmod_mode = 0000,
+		  .orig.how.flags = O_PATH, .orig.mode = 0050,
+		  .orig.how.upgrade_mask = UPGRADE_NOWRITE,
+		  .new.how.flags  = O_WRONLY, .new.mode   = 0300, .new.err = err_access },
+		{ .open = sys_openat2,  .chmod_mode = 0000,
+		  .orig.how.flags = O_PATH, .orig.mode = 0030,
+		  .orig.how.upgrade_mask = UPGRADE_NOREAD,
+		  .new.how.flags  =   O_RDWR, .new.mode   = 0700, .new.err = err_access },
+		{ .open = sys_openat2,  .chmod_mode = 0000,
+		  .orig.how.flags = O_PATH, .orig.mode = 0050,
+		  .orig.how.upgrade_mask = UPGRADE_NOWRITE,
+		  .new.how.flags  =   O_RDWR, .new.mode   = 0700, .new.err = err_access },
+	};
+
+	BUILD_BUG_ON(ARRAY_LEN(tests) != NUM_REOPEN_TESTS);
+
+	for (int i = 0; i < ARRAY_LEN(tests); i++) {
+		int fd;
+		char *orig_flagset, *new_flagset;
+		struct reopen_test *test = &tests[i];
+		void (*resultfn)(const char *msg, ...) = ksft_test_result_pass;
+
+		E_chmod(tmpfile, test->chmod_mode);
+
+		fd = test->open(AT_FDCWD, tmpfile, &test->orig.how);
+		E_assert(fd >= 0, "open '%s' failed: %m\n", tmpfile);
+
+		/* Make sure that any EACCES we see is not from inode permissions. */
+		E_chmod(tmpfile, 0777);
+
+		if (reopen(fd, test))
+			resultfn = ksft_test_result_fail;
+
+		close(fd);
+
+		new_flagset = openat_flags(test->new.how.flags);
+		if (test->open == sys_openat)
+			orig_flagset = openat_flags(test->orig.how.flags);
+		else if (test->open == sys_openat2)
+			orig_flagset = openat2_flags(&test->orig.how);
+		else
+			ksft_exit_fail_msg("unknown test->open\n");
+
+		resultfn("%sordinary reopen of (orig[%s]=%s, new=%s) chmod=%.3o %s\n",
+			 privileged ? "privileged " : "",
+			 test->open == sys_openat ? "openat" : "openat2",
+			 orig_flagset, new_flagset, test->chmod_mode,
+			 test->new.err < 0 ? strerror(-test->new.err) : "works");
+		fflush(stdout);
+
+		free(new_flagset);
+		free(orig_flagset);
+	}
+
+	unlink(tmpfile);
+}
+
+#define NUM_CLOEXEC_TESTS 1
+
+void test_openat2_cloexec_test(void)
+{
+	void (*resultfn)(const char *msg, ...) = ksft_test_result_pass;
+	struct open_how how = {
+		.flags = O_CLOEXEC | O_PATH | O_DIRECTORY,
+	};
+
+	int fd = sys_openat2(AT_FDCWD, ".", &how);
+	E_assert(fd >= 0, "open '.' failed: %m\n");
+
+	int flags = fcntl(fd, F_GETFD);
+	E_assert(flags >= 0, "F_GETFD failed: %m\n");
+
+	if (!(flags & FD_CLOEXEC))
+		resultfn = ksft_test_result_fail;
+
+	resultfn("openat2(O_CLOEXEC) works as expected\n");
+}
+
+int main(int argc, char **argv)
+{
+	bool privileged;
+
+	ksft_print_header();
+	ksft_set_plan(2 * NUM_REOPEN_TESTS + NUM_CLOEXEC_TESTS);
+	test_openat2_supported();
+
+	/*
+	 * Technically we should be checking CAP_DAC_OVERRIDE, but it's easier to
+	 * just assume that euid=0 has the full capability set.
+	 */
+	privileged = (geteuid() == 0);
+	if (!privileged)
+		ksft_test_result_skip("privileged tests require euid == 0\n");
+	else {
+		test_reopen_ordinary(privileged);
+
+		E_setresuid(65534, 65534, 65534);
+		privileged = (geteuid() == 0);
+	}
+
+	test_reopen_ordinary(privileged);
+	test_openat2_cloexec_test();
+
+	if (ksft_get_fail_cnt() + ksft_get_error_cnt() > 0)
+		ksft_exit_fail();
+	else
+		ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/openat2/rename_attack_test.c b/tools/testing/selftests/openat2/rename_attack_test.c
new file mode 100644
index 000000000000..39b20ea185d5
--- /dev/null
+++ b/tools/testing/selftests/openat2/rename_attack_test.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Author: Aleksa Sarai <cyphar@cyphar.com>
+ * Copyright (C) 2018-2019 SUSE LLC.
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <sys/mman.h>
+#include <sys/prctl.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <syscall.h>
+#include <limits.h>
+#include <unistd.h>
+
+#include "../kselftest.h"
+#include "helpers.h"
+
+/* Construct a test directory with the following structure:
+ *
+ * root/
+ * |-- a/
+ * |   `-- c/
+ * `-- b/
+ */
+int setup_testdir(void)
+{
+	int dfd;
+	char dirname[] = "/tmp/ksft-openat2-rename-attack.XXXXXX";
+
+	/* Make the top-level directory. */
+	if (!mkdtemp(dirname))
+		ksft_exit_fail_msg("setup_testdir: failed to create tmpdir\n");
+	dfd = open(dirname, O_PATH | O_DIRECTORY);
+	if (dfd < 0)
+		ksft_exit_fail_msg("setup_testdir: failed to open tmpdir\n");
+
+	E_mkdirat(dfd, "a", 0755);
+	E_mkdirat(dfd, "b", 0755);
+	E_mkdirat(dfd, "a/c", 0755);
+
+	return dfd;
+}
+
+/* Swap @dirfd/@a and @dirfd/@b constantly. Parent must kill this process. */
+pid_t spawn_attack(int dirfd, char *a, char *b)
+{
+	pid_t child = fork();
+	if (child != 0)
+		return child;
+
+	/* If the parent (the test process) dies, kill ourselves too. */
+	prctl(PR_SET_PDEATHSIG, SIGKILL);
+
+	/* Swap @a and @b. */
+	for (;;)
+		renameat2(dirfd, a, dirfd, b, RENAME_EXCHANGE);
+	exit(1);
+}
+
+#define NUM_RENAME_TESTS 1
+#define ROUNDS 400000
+
+void test_rename_attack(void)
+{
+	int dfd, afd, escaped_count = 0;
+	void (*resultfn)(const char *msg, ...) = ksft_test_result_pass;
+	pid_t child;
+
+	dfd = setup_testdir();
+	afd = openat(dfd, "a", O_PATH);
+	if (afd < 0)
+		ksft_exit_fail_msg("test_rename_attack: failed to open 'a'\n");
+
+	child = spawn_attack(dfd, "a/c", "b");
+
+	for (int i = 0; i < ROUNDS; i++) {
+		int fd;
+		bool failed;
+		struct open_how how = {
+			.flags = O_PATH,
+			.resolve = RESOLVE_IN_ROOT,
+		};
+		char *victim_path = "c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../..";
+
+		fd = sys_openat2(afd, victim_path, &how);
+		if (fd < 0)
+			failed = (fd != -EXDEV);
+		else
+			failed = !fdequal(fd, afd, NULL);
+
+		escaped_count += failed;
+		close(fd);
+	}
+
+	if (escaped_count > 0)
+		resultfn = ksft_test_result_fail;
+
+	resultfn("rename attack fails (expected 0 breakouts in %d runs, got %d)\n",
+		 ROUNDS, escaped_count);
+
+	/* Should be killed anyway, but might as well make sure. */
+	kill(child, SIGKILL);
+}
+
+int main(int argc, char **argv)
+{
+	ksft_print_header();
+	ksft_set_plan(NUM_RENAME_TESTS);
+	test_openat2_supported();
+
+	test_rename_attack();
+
+	if (ksft_get_fail_cnt() + ksft_get_error_cnt() > 0)
+		ksft_exit_fail();
+	else
+		ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/openat2/resolve_test.c b/tools/testing/selftests/openat2/resolve_test.c
new file mode 100644
index 000000000000..8ef3dbb7edbe
--- /dev/null
+++ b/tools/testing/selftests/openat2/resolve_test.c
@@ -0,0 +1,402 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Author: Aleksa Sarai <cyphar@cyphar.com>
+ * Copyright (C) 2018-2019 SUSE LLC.
+ */
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <sched.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+
+#include "../kselftest.h"
+#include "helpers.h"
+
+/*
+ * Construct a test directory with the following structure:
+ *
+ * root/
+ * |-- procexe -> /proc/self/exe
+ * |-- procroot -> /proc/self/root
+ * |-- root/
+ * |-- mnt/ [mountpoint]
+ * |   |-- self -> ../mnt/
+ * |   `-- absself -> /mnt/
+ * |-- etc/
+ * |   `-- passwd
+ * |-- creatlink -> /newfile3
+ * |-- relsym -> etc/passwd
+ * |-- abssym -> /etc/passwd
+ * |-- abscheeky -> /cheeky
+ * |-- abscheeky -> /cheeky
+ * `-- cheeky/
+ *     |-- absself -> /
+ *     |-- self -> ../../root/
+ *     |-- garbageself -> /../../root/
+ *     |-- passwd -> ../cheeky/../cheeky/../etc/../etc/passwd
+ *     |-- abspasswd -> /../cheeky/../cheeky/../etc/../etc/passwd
+ *     |-- dotdotlink -> ../../../../../../../../../../../../../../etc/passwd
+ *     `-- garbagelink -> /../../../../../../../../../../../../../../etc/passwd
+ */
+int setup_testdir(void)
+{
+	int dfd, tmpfd;
+	char dirname[] = "/tmp/ksft-openat2-testdir.XXXXXX";
+
+	/* Unshare and make /tmp a new directory. */
+	E_unshare(CLONE_NEWNS);
+	E_mount("", "/tmp", "", MS_PRIVATE, "");
+
+	/* Make the top-level directory. */
+	if (!mkdtemp(dirname))
+		ksft_exit_fail_msg("setup_testdir: failed to create tmpdir\n");
+	dfd = open(dirname, O_PATH | O_DIRECTORY);
+	if (dfd < 0)
+		ksft_exit_fail_msg("setup_testdir: failed to open tmpdir\n");
+
+	/* A sub-directory which is actually used for tests. */
+	E_mkdirat(dfd, "root", 0755);
+	tmpfd = openat(dfd, "root", O_PATH | O_DIRECTORY);
+	if (tmpfd < 0)
+		ksft_exit_fail_msg("setup_testdir: failed to open tmpdir\n");
+	close(dfd);
+	dfd = tmpfd;
+
+	E_symlinkat("/proc/self/exe", dfd, "procexe");
+	E_symlinkat("/proc/self/root", dfd, "procroot");
+	E_mkdirat(dfd, "root", 0755);
+
+	/* There is no mountat(2), so use chdir. */
+	E_mkdirat(dfd, "mnt", 0755);
+	E_fchdir(dfd);
+	E_mount("tmpfs", "./mnt", "tmpfs", MS_NOSUID | MS_NODEV, "");
+	E_symlinkat("../mnt/", dfd, "mnt/self");
+	E_symlinkat("/mnt/", dfd, "mnt/absself");
+
+	E_mkdirat(dfd, "etc", 0755);
+	E_touchat(dfd, "etc/passwd");
+
+	E_symlinkat("/newfile3", dfd, "creatlink");
+	E_symlinkat("etc/passwd", dfd, "relsym");
+	E_symlinkat("/etc/passwd", dfd, "abssym");
+	E_symlinkat("/cheeky", dfd, "abscheeky");
+
+	E_mkdirat(dfd, "cheeky", 0755);
+
+	E_symlinkat("/", dfd, "cheeky/absself");
+	E_symlinkat("../../root/", dfd, "cheeky/self");
+	E_symlinkat("/../../root/", dfd, "cheeky/garbageself");
+
+	E_symlinkat("../cheeky/../etc/../etc/passwd", dfd, "cheeky/passwd");
+	E_symlinkat("/../cheeky/../etc/../etc/passwd", dfd, "cheeky/abspasswd");
+
+	E_symlinkat("../../../../../../../../../../../../../../etc/passwd",
+		    dfd, "cheeky/dotdotlink");
+	E_symlinkat("/../../../../../../../../../../../../../../etc/passwd",
+		    dfd, "cheeky/garbagelink");
+
+	return dfd;
+}
+
+struct basic_test {
+	const char *dir;
+	const char *path;
+	struct open_how how;
+	bool pass;
+	union {
+		int err;
+		const char *path;
+	} out;
+};
+
+#define NUM_OPENAT2_OPATH_TESTS 84
+
+void test_openat2_opath_tests(void)
+{
+	int rootfd;
+	char *procselfexe;
+
+	E_asprintf(&procselfexe, "/proc/%d/exe", getpid());
+	rootfd = setup_testdir();
+
+	struct basic_test tests[] = {
+		/** RESOLVE_BENEATH **/
+		/* Attempts to cross dirfd should be blocked. */
+		{ .path = "/",			.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "cheeky/absself",	.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "abscheeky/absself",	.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "..",			.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "../root/",		.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "cheeky/self",	.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "abscheeky/self",	.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "cheeky/garbageself",	.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "abscheeky/garbageself", .how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		/* Only relative paths that stay inside dirfd should work. */
+		{ .path = "root",		.how.resolve = RESOLVE_BENEATH,
+		  .out.path = "root",		.pass = true },
+		{ .path = "etc",		.how.resolve = RESOLVE_BENEATH,
+		  .out.path = "etc",		.pass = true },
+		{ .path = "etc/passwd",		.how.resolve = RESOLVE_BENEATH,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "relsym",		.how.resolve = RESOLVE_BENEATH,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "cheeky/passwd",	.how.resolve = RESOLVE_BENEATH,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "abscheeky/passwd",	.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "abssym",		.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "/etc/passwd",	.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "cheeky/abspasswd",	.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "abscheeky/abspasswd", .how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		/* Tricky paths should fail. */
+		{ .path = "cheeky/dotdotlink",	.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "abscheeky/dotdotlink", .how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "cheeky/garbagelink",	.how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "abscheeky/garbagelink", .how.resolve = RESOLVE_BENEATH,
+		  .out.err = -EXDEV,		.pass = false },
+
+		/** RESOLVE_IN_ROOT **/
+		/* All attempts to cross the dirfd will be scoped-to-root. */
+		{ .path = "/",			.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = NULL,		.pass = true },
+		{ .path = "cheeky/absself",	.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = NULL,		.pass = true },
+		{ .path = "abscheeky/absself",	.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = NULL,		.pass = true },
+		{ .path = "..",			.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = NULL,		.pass = true },
+		{ .path = "../root/",		.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "root",		.pass = true },
+		{ .path = "../root/",		.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "root",		.pass = true },
+		{ .path = "cheeky/self",	.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "root",		.pass = true },
+		{ .path = "cheeky/garbageself",	.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "root",		.pass = true },
+		{ .path = "abscheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "root",		.pass = true },
+		{ .path = "root",		.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "root",		.pass = true },
+		{ .path = "etc",		.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc",		.pass = true },
+		{ .path = "etc/passwd",		.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "relsym",		.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "cheeky/passwd",	.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "abscheeky/passwd",	.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "abssym",		.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "/etc/passwd",	.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "cheeky/abspasswd",	.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "abscheeky/abspasswd", .how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "cheeky/dotdotlink",	.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "abscheeky/dotdotlink", .how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "/../../../../abscheeky/dotdotlink", .how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "cheeky/garbagelink",	.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "abscheeky/garbagelink", .how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		{ .path = "/../../../../abscheeky/garbagelink", .how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "etc/passwd",	.pass = true },
+		/* O_CREAT should handle trailing symlinks correctly. */
+		{ .path = "newfile1",		.how.flags = O_CREAT,
+						.how.mode = 0700,
+						.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "newfile1",	.pass = true },
+		{ .path = "/newfile2",		.how.flags = O_CREAT,
+						.how.mode = 0700,
+						.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "newfile2",	.pass = true },
+		{ .path = "/creatlink",		.how.flags = O_CREAT,
+						.how.mode = 0700,
+						.how.resolve = RESOLVE_IN_ROOT,
+		  .out.path = "newfile3",	.pass = true },
+
+		/** RESOLVE_NO_XDEV **/
+		/* Crossing *down* into a mountpoint is disallowed. */
+		{ .path = "mnt",		.how.resolve = RESOLVE_NO_XDEV,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "mnt/",		.how.resolve = RESOLVE_NO_XDEV,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "mnt/.",		.how.resolve = RESOLVE_NO_XDEV,
+		  .out.err = -EXDEV,		.pass = false },
+		/* Crossing *up* out of a mountpoint is disallowed. */
+		{ .dir = "mnt", .path = ".",	.how.resolve = RESOLVE_NO_XDEV,
+		  .out.path = "mnt",		.pass = true },
+		{ .dir = "mnt", .path = "..",	.how.resolve = RESOLVE_NO_XDEV,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .dir = "mnt", .path = "../mnt", .how.resolve = RESOLVE_NO_XDEV,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .dir = "mnt", .path = "self",	.how.resolve = RESOLVE_NO_XDEV,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .dir = "mnt", .path = "absself", .how.resolve = RESOLVE_NO_XDEV,
+		  .out.err = -EXDEV,		.pass = false },
+		/* Jumping to "/" is ok, but later components cannot cross. */
+		{ .dir = "mnt", .path = "/",	.how.resolve = RESOLVE_NO_XDEV,
+		  .out.path = "/",		.pass = true },
+		{ .dir = "/", .path = "/",	.how.resolve = RESOLVE_NO_XDEV,
+		  .out.path = "/",		.pass = true },
+		{ .path = "/proc/1",		.how.resolve = RESOLVE_NO_XDEV,
+		  .out.err = -EXDEV,		.pass = false },
+		{ .path = "/tmp",		.how.resolve = RESOLVE_NO_XDEV,
+		  .out.err = -EXDEV,		.pass = false },
+
+		/** RESOLVE_NO_MAGICLINKS **/
+		/* Regular symlinks should work. */
+		{ .path = "relsym",		.how.resolve = RESOLVE_NO_MAGICLINKS,
+		  .out.path = "etc/passwd",	.pass = true },
+		/* Magic-links should not work. */
+		{ .path = "procexe",		.how.resolve = RESOLVE_NO_MAGICLINKS,
+		  .out.err = -ELOOP,		.pass = false },
+		{ .path = "/proc/self/exe",	.how.resolve = RESOLVE_NO_MAGICLINKS,
+		  .out.err = -ELOOP,		.pass = false },
+		{ .path = "procroot/etc",	.how.resolve = RESOLVE_NO_MAGICLINKS,
+		  .out.err = -ELOOP,		.pass = false },
+		{ .path = "/proc/self/root/etc", .how.resolve = RESOLVE_NO_MAGICLINKS,
+		  .out.err = -ELOOP,		.pass = false },
+		{ .path = "/proc/self/root/etc", .how.flags = O_NOFOLLOW,
+						 .how.resolve = RESOLVE_NO_MAGICLINKS,
+		  .out.err = -ELOOP,		.pass = false },
+		{ .path = "/proc/self/exe",	.how.flags = O_NOFOLLOW,
+						.how.resolve = RESOLVE_NO_MAGICLINKS,
+		  .out.path = procselfexe,	.pass = true },
+
+		/** RESOLVE_NO_SYMLINKS **/
+		/* Normal paths should work. */
+		{ .path = ".",			.how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.path = NULL,		.pass = true },
+		{ .path = "root",		.how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.path = "root",		.pass = true },
+		{ .path = "etc",		.how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.path = "etc",		.pass = true },
+		{ .path = "etc/passwd",		.how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.path = "etc/passwd",	.pass = true },
+		/* Regular symlinks are blocked. */
+		{ .path = "relsym",		.how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.err = -ELOOP,		.pass = false },
+		{ .path = "abssym",		.how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.err = -ELOOP,		.pass = false },
+		{ .path = "cheeky/garbagelink",	.how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.err = -ELOOP,		.pass = false },
+		{ .path = "abscheeky/garbagelink", .how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.err = -ELOOP,		.pass = false },
+		{ .path = "abscheeky/absself",	.how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.err = -ELOOP,		.pass = false },
+		/* Trailing symlinks with NO_FOLLOW. */
+		{ .path = "relsym",		.how.flags = O_NOFOLLOW,
+						.how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.path = "relsym",		.pass = true },
+		{ .path = "abssym",		.how.flags = O_NOFOLLOW,
+						.how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.path = "abssym",		.pass = true },
+		{ .path = "cheeky/garbagelink",	.how.flags = O_NOFOLLOW,
+						.how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.path = "cheeky/garbagelink", .pass = true },
+		{ .path = "abscheeky/garbagelink", .how.flags = O_NOFOLLOW,
+						   .how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.err = -ELOOP,		.pass = false },
+		{ .path = "abscheeky/absself",	.how.flags = O_NOFOLLOW,
+						.how.resolve = RESOLVE_NO_SYMLINKS,
+		  .out.err = -ELOOP,		.pass = false },
+	};
+
+	BUILD_BUG_ON(ARRAY_LEN(tests) != NUM_OPENAT2_OPATH_TESTS);
+
+	for (int i = 0; i < ARRAY_LEN(tests); i++) {
+		int dfd, fd;
+		bool failed;
+		void (*resultfn)(const char *msg, ...) = ksft_test_result_pass;
+		struct basic_test *test = &tests[i];
+		char *flagstr;
+
+		/* Auto-set O_PATH. */
+		if (!(test->how.flags & O_CREAT))
+			test->how.flags |= O_PATH;
+		flagstr = openat2_flags(&test->how);
+
+		if (test->dir)
+			dfd = openat(rootfd, test->dir, O_PATH | O_DIRECTORY);
+		else
+			dfd = dup(rootfd);
+		if (dfd < 0) {
+			resultfn = ksft_test_result_error;
+			goto next;
+		}
+
+		fd = sys_openat2(dfd, test->path, &test->how);
+		if (test->pass)
+			failed = (fd < 0 || !fdequal(fd, rootfd, test->out.path));
+		else
+			failed = (fd != test->out.err);
+		if (fd >= 0)
+			close(fd);
+		close(dfd);
+
+		if (failed)
+			resultfn = ksft_test_result_fail;
+
+next:
+		if (test->pass)
+			resultfn("openat2(root[%s], %s, %s) ==> %s\n",
+				 test->dir ?: ".", test->path, flagstr,
+				 test->out.path ?: ".");
+		else
+			resultfn("openat2(root[%s], %s, %s) ==> %d (%s)\n",
+				 test->dir ?: ".", test->path, flagstr,
+				 test->out.err, strerror(-test->out.err));
+		fflush(stdout);
+
+		free(flagstr);
+	}
+
+	free(procselfexe);
+	close(rootfd);
+}
+
+int main(int argc, char **argv)
+{
+	ksft_print_header();
+	ksft_set_plan(NUM_OPENAT2_OPATH_TESTS);
+	test_openat2_supported();
+
+	/* NOTE: We should be checking for CAP_SYS_ADMIN here... */
+	if (geteuid() != 0)
+		ksft_exit_skip("openat2(2) tests require euid == 0\n");
+
+	test_openat2_opath_tests();
+
+	if (ksft_get_fail_cnt() + ksft_get_error_cnt() > 0)
+		ksft_exit_fail();
+	else
+		ksft_exit_pass();
+}
-- 
2.22.0



^ permalink raw reply related

* Re: [PATCH] btrfs: fix allocation of bitmap pages.
From: Vlastimil Babka @ 2019-08-20 11:06 UTC (permalink / raw)
  To: Christoph Hellwig, dsterba, Christophe Leroy, erhard_f,
	Chris Mason, Josef Bacik, David Sterba, Andrew Morton,
	linux-kernel, linuxppc-dev, linux-btrfs, linux-mm, stable
In-Reply-To: <20190820023031.GC9594@infradead.org>

On 8/20/19 4:30 AM, Christoph Hellwig wrote:
> On Mon, Aug 19, 2019 at 07:46:00PM +0200, David Sterba wrote:
>> Another thing that is lost is the slub debugging support for all
>> architectures, because get_zeroed_pages lacking the red zones and sanity
>> checks.
>> 
>> I find working with raw pages in this code a bit inconsistent with the
>> rest of btrfs code, but that's rather minor compared to the above.
>> 
>> Summing it up, I think that the proper fix should go to copy_page
>> implementation on architectures that require it or make it clear what
>> are the copy_page constraints.
> 
> The whole point of copy_page is to copy exactly one page and it makes
> sense to assume that is aligned.  A sane memcpy would use the same
> underlying primitives as well after checking they fit.  So I think the
> prime issue here is btrfs' use of copy_page instead of memcpy.  The
> secondary issue is slub fucking up alignments for no good reason.  We
> just got bitten by that crap again in XFS as well :(

Meh, I should finally get back to https://lwn.net/Articles/787740/ right



^ permalink raw reply

* Re: [PATCH v2 1/2] kasan: support instrumented bitops combined with generic bitops
From: Marco Elver @ 2019-08-20  9:55 UTC (permalink / raw)
  To: Daniel Axtens
  Cc: linux-s390, the arch/x86 maintainers, kasan-dev, linux-arch,
	linuxppc-dev
In-Reply-To: <20190820024941.12640-1-dja@axtens.net>

On Tue, 20 Aug 2019 at 04:50, Daniel Axtens <dja@axtens.net> wrote:
>
> Currently bitops-instrumented.h assumes that the architecture provides
> atomic, non-atomic and locking bitops (e.g. both set_bit and __set_bit).
> This is true on x86 and s390, but is not always true: there is a
> generic bitops/non-atomic.h header that provides generic non-atomic
> operations, and also a generic bitops/lock.h for locking operations.
>
> powerpc uses the generic non-atomic version, so it does not have it's
> own e.g. __set_bit that could be renamed arch___set_bit.
>
> Split up bitops-instrumented.h to mirror the atomic/non-atomic/lock
> split. This allows arches to only include the headers where they
> have arch-specific versions to rename. Update x86 and s390.
>
> (The generic operations are automatically instrumented because they're
> written in C, not asm.)
>
> Suggested-by: Christophe Leroy <christophe.leroy@c-s.fr>
> Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
> Signed-off-by: Daniel Axtens <dja@axtens.net>

Acked-by: Marco Elver <elver@google.com>

Thanks!

^ permalink raw reply

* [PATCH RESEND v11 0/8] openat2(2)
From: Aleksa Sarai @ 2019-08-20  3:33 UTC (permalink / raw)
  To: Al Viro, Jeff Layton, J. Bruce Fields, Arnd Bergmann,
	David Howells, Shuah Khan, Shuah Khan
  Cc: linux-ia64, linux-sh, Alexei Starovoitov, Oleg Nesterov,
	linux-kselftest, sparclinux, linux-arch, linux-s390,
	Tycho Andersen, Aleksa Sarai, linux-arm-kernel, linux-mips,
	linux-xtensa, Kees Cook, Jann Horn, linuxppc-dev, Aleksa Sarai,
	Andy Lutomirski, David Drysdale, Christian Brauner, linux-parisc,
	linux-m68k, linux-api, containers, linux-kernel, Eric Biederman,
	linux-alpha, linux-fsdevel, Andrew Morton, Linus Torvalds,
	Chanho Min

This patchset is being developed here:
    <https://github.com/cyphar/linux/tree/resolveat/master>

Patch changelog:
 v11: [RESEND: <https://lore.kernel.org/lkml/20190728010207.9781-1-cyphar@cyphar.com/>]
    * Fix checkpatch.pl errors and warnings where reasonable.
    * Minor cleanup to pr_warn logging for may_open_magiclink().
    * Drop kselftests patch to handle %m formatting correctly, and send
      it through the kselftests tree directly. [Shuah Khan]
 v10: <https://lore.kernel.org/lkml/20190719164225.27083-1-cyphar@cyphar.com/>
 v09: <https://lore.kernel.org/lkml/20190706145737.5299-1-cyphar@cyphar.com/>
 v08: <https://lore.kernel.org/lkml/20190520133305.11925-1-cyphar@cyphar.com/>
 v07: <https://lore.kernel.org/lkml/20190507164317.13562-1-cyphar@cyphar.com/>
 v06: <https://lore.kernel.org/lkml/20190506165439.9155-1-cyphar@cyphar.com/>
 v05: <https://lore.kernel.org/lkml/20190320143717.2523-1-cyphar@cyphar.com/>
 v04: <https://lore.kernel.org/lkml/20181112142654.341-1-cyphar@cyphar.com/>
 v03: <https://lore.kernel.org/lkml/20181009070230.12884-1-cyphar@cyphar.com/>
 v02: <https://lore.kernel.org/lkml/20181009065300.11053-1-cyphar@cyphar.com/>
 v01: <https://lore.kernel.org/lkml/20180929103453.12025-1-cyphar@cyphar.com/>

The need for some sort of control over VFS's path resolution (to avoid
malicious paths resulting in inadvertent breakouts) has been a very
long-standing desire of many userspace applications. This patchset is a
revival of Al Viro's old AT_NO_JUMPS[1,2] patchset (which was a variant
of David Drysdale's O_BENEATH patchset[3] which was a spin-off of the
Capsicum project[4]) with a few additions and changes made based on the
previous discussion within [5] as well as others I felt were useful.

In line with the conclusions of the original discussion of AT_NO_JUMPS,
the flag has been split up into separate flags. However, instead of
being an openat(2) flag it is provided through a new syscall openat2(2)
which provides several other improvements to the openat(2) interface (see the
patch description for more details). The following new LOOKUP_* flags are
added:

  * LOOKUP_NO_XDEV blocks all mountpoint crossings (upwards, downwards,
    or through absolute links). Absolute pathnames alone in openat(2) do
    not trigger this.

  * LOOKUP_NO_MAGICLINKS blocks resolution through /proc/$pid/fd-style
    links. This is done by blocking the usage of nd_jump_link() during
    resolution in a filesystem. The term "magic-links" is used to match
    with the only reference to these links in Documentation/, but I'm
    happy to change the name.

    It should be noted that this is different to the scope of
    ~LOOKUP_FOLLOW in that it applies to all path components. However,
    you can do openat2(NO_FOLLOW|NO_MAGICLINKS) on a magic-link and it
    will *not* fail (assuming that no parent component was a
    magic-link), and you will have an fd for the magic-link.

  * LOOKUP_BENEATH disallows escapes to outside the starting dirfd's
    tree, using techniques such as ".." or absolute links. Absolute
    paths in openat(2) are also disallowed. Conceptually this flag is to
    ensure you "stay below" a certain point in the filesystem tree --
    but this requires some additional to protect against various races
    that would allow escape using "..".

    Currently LOOKUP_BENEATH implies LOOKUP_NO_MAGICLINKS, because it
    can trivially beam you around the filesystem (breaking the
    protection). In future, there might be similar safety checks done as
    in LOOKUP_IN_ROOT, but that requires more discussion.

In addition, two new flags are added that expand on the above ideas:

  * LOOKUP_NO_SYMLINKS does what it says on the tin. No symlink
    resolution is allowed at all, including magic-links. Just as with
    LOOKUP_NO_MAGICLINKS this can still be used with NOFOLLOW to open an
    fd for the symlink as long as no parent path had a symlink
    component.

  * LOOKUP_IN_ROOT is an extension of LOOKUP_BENEATH that, rather than
    blocking attempts to move past the root, forces all such movements
    to be scoped to the starting point. This provides chroot(2)-like
    protection but without the cost of a chroot(2) for each filesystem
    operation, as well as being safe against race attacks that chroot(2)
    is not.

    If a race is detected (as with LOOKUP_BENEATH) then an error is
    generated, and similar to LOOKUP_BENEATH it is not permitted to cross
    magic-links with LOOKUP_IN_ROOT.

    The primary need for this is from container runtimes, which
    currently need to do symlink scoping in userspace[6] when opening
    paths in a potentially malicious container. There is a long list of
    CVEs that could have bene mitigated by having RESOLVE_THIS_ROOT
    (such as CVE-2017-1002101, CVE-2017-1002102, CVE-2018-15664, and
    CVE-2019-5736, just to name a few).

And further, several semantics of file descriptor "re-opening" are now
changed to prevent attacks like CVE-2019-5736 by restricting how
magic-links can be resolved (based on their mode). This required some
other changes to the semantics of the modes of O_PATH file descriptor's
associated /proc/self/fd magic-links. openat2(2) has the ability to
further restrict re-opening of its own O_PATH fds, so that users can
make even better use of this feature.

Finally, O_EMPTYPATH was added so that users can do /proc/self/fd-style
re-opening without depending on procfs. The new restricted semantics for
magic-links are applied here too.

In order to make all of the above more usable, I'm working on
libpathrs[7] which is a C-friendly library for safe path resolution. It
features a userspace-emulated backend if the kernel doesn't support
openat2(2). Hopefully we can get userspace to switch to using it, and
thus get openat2(2) support for free once it's ready.

Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Christian Brauner <christian@brauner.io>
Cc: David Drysdale <drysdale@google.com>
Cc: Tycho Andersen <tycho@tycho.ws>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: <containers@lists.linux-foundation.org>
Cc: <linux-fsdevel@vger.kernel.org>
Cc: <linux-api@vger.kernel.org>

[1]: https://lwn.net/Articles/721443/
[2]: https://lore.kernel.org/patchwork/patch/784221/
[3]: https://lwn.net/Articles/619151/
[4]: https://lwn.net/Articles/603929/
[5]: https://lwn.net/Articles/723057/
[6]: https://github.com/cyphar/filepath-securejoin
[7]: https://github.com/openSUSE/libpathrs

Aleksa Sarai (8):
  namei: obey trailing magic-link DAC permissions
  procfs: switch magic-link modes to be more sane
  open: O_EMPTYPATH: procfs-less file descriptor re-opening
  namei: O_BENEATH-style path resolution flags
  namei: LOOKUP_IN_ROOT: chroot-like path resolution
  namei: aggressively check for nd->root escape on ".." resolution
  open: openat2(2) syscall
  selftests: add openat2(2) selftests

 Documentation/filesystems/path-lookup.rst     |  12 +-
 arch/alpha/include/uapi/asm/fcntl.h           |   1 +
 arch/alpha/kernel/syscalls/syscall.tbl        |   1 +
 arch/arm/tools/syscall.tbl                    |   1 +
 arch/arm64/include/asm/unistd.h               |   2 +-
 arch/arm64/include/asm/unistd32.h             |   2 +
 arch/ia64/kernel/syscalls/syscall.tbl         |   1 +
 arch/m68k/kernel/syscalls/syscall.tbl         |   1 +
 arch/microblaze/kernel/syscalls/syscall.tbl   |   1 +
 arch/mips/kernel/syscalls/syscall_n32.tbl     |   1 +
 arch/mips/kernel/syscalls/syscall_n64.tbl     |   1 +
 arch/mips/kernel/syscalls/syscall_o32.tbl     |   1 +
 arch/parisc/include/uapi/asm/fcntl.h          |  39 +-
 arch/parisc/kernel/syscalls/syscall.tbl       |   1 +
 arch/powerpc/kernel/syscalls/syscall.tbl      |   1 +
 arch/s390/kernel/syscalls/syscall.tbl         |   1 +
 arch/sh/kernel/syscalls/syscall.tbl           |   1 +
 arch/sparc/include/uapi/asm/fcntl.h           |   1 +
 arch/sparc/kernel/syscalls/syscall.tbl        |   1 +
 arch/x86/entry/syscalls/syscall_32.tbl        |   1 +
 arch/x86/entry/syscalls/syscall_64.tbl        |   1 +
 arch/xtensa/kernel/syscalls/syscall.tbl       |   1 +
 fs/fcntl.c                                    |   2 +-
 fs/internal.h                                 |   1 +
 fs/namei.c                                    | 270 ++++++++++--
 fs/open.c                                     | 112 ++++-
 fs/proc/base.c                                |  20 +-
 fs/proc/fd.c                                  |  23 +-
 fs/proc/namespaces.c                          |   2 +-
 include/linux/fcntl.h                         |  17 +-
 include/linux/fs.h                            |   8 +-
 include/linux/namei.h                         |   9 +
 include/linux/syscalls.h                      |  17 +-
 include/uapi/asm-generic/fcntl.h              |   4 +
 include/uapi/asm-generic/unistd.h             |   5 +-
 include/uapi/linux/fcntl.h                    |  42 ++
 tools/testing/selftests/Makefile              |   1 +
 tools/testing/selftests/memfd/memfd_test.c    |   7 +-
 tools/testing/selftests/openat2/.gitignore    |   1 +
 tools/testing/selftests/openat2/Makefile      |   8 +
 tools/testing/selftests/openat2/helpers.c     | 162 +++++++
 tools/testing/selftests/openat2/helpers.h     | 116 +++++
 .../testing/selftests/openat2/linkmode_test.c | 333 +++++++++++++++
 .../selftests/openat2/rename_attack_test.c    | 127 ++++++
 .../testing/selftests/openat2/resolve_test.c  | 402 ++++++++++++++++++
 45 files changed, 1655 insertions(+), 107 deletions(-)
 create mode 100644 tools/testing/selftests/openat2/.gitignore
 create mode 100644 tools/testing/selftests/openat2/Makefile
 create mode 100644 tools/testing/selftests/openat2/helpers.c
 create mode 100644 tools/testing/selftests/openat2/helpers.h
 create mode 100644 tools/testing/selftests/openat2/linkmode_test.c
 create mode 100644 tools/testing/selftests/openat2/rename_attack_test.c
 create mode 100644 tools/testing/selftests/openat2/resolve_test.c

-- 
2.22.0


^ permalink raw reply

* [PATCH RESEND v11 7/8] open: openat2(2) syscall
From: Aleksa Sarai @ 2019-08-20  3:34 UTC (permalink / raw)
  To: Al Viro, Jeff Layton, J. Bruce Fields, Arnd Bergmann,
	David Howells, Shuah Khan, Shuah Khan
  Cc: linux-ia64, linux-sh, Alexei Starovoitov, Oleg Nesterov,
	linux-kselftest, sparclinux, linux-arch, linux-s390,
	Tycho Andersen, Aleksa Sarai, linux-arm-kernel, linux-mips,
	linux-xtensa, Kees Cook, Jann Horn, linuxppc-dev, Aleksa Sarai,
	Andy Lutomirski, David Drysdale, Christian Brauner, linux-parisc,
	linux-m68k, linux-api, Chanho Min, linux-kernel, Eric Biederman,
	linux-alpha, linux-fsdevel, Andrew Morton, Linus Torvalds,
	containers
In-Reply-To: <20190820033406.29796-1-cyphar@cyphar.com>

The most obvious syscall to add support for the new LOOKUP_* scoping
flags would be openat(2). However, there are a few reasons why this is
not the best course of action:

 * The new LOOKUP_* flags are intended to be security features, and
   openat(2) will silently ignore all unknown flags. This means that
   users would need to avoid foot-gunning themselves constantly when
   using this interface if it were part of openat(2). This can be fixed
   by having userspace libraries handle this for users[1], but should be
   avoided if possible.

 * Resolution scoping feels like a different operation to the existing
   O_* flags. And since openat(2) has limited flag space, it seems to be
   quite wasteful to clutter it with 5 flags that are all
   resolution-related. Arguably O_NOFOLLOW is also a resolution flag but
   its entire purpose is to error out if you encounter a trailing
   symlink -- not to scope resolution.

 * Other systems would be able to reimplement this syscall allowing for
   cross-OS standardisation rather than being hidden amongst O_* flags
   which may result in it not being used by all the parties that might
   want to use it (file servers, web servers, container runtimes, etc).

 * It gives us the opportunity to iterate on the O_PATH interface. In
   particular, the new @how->upgrade_mask field for fd re-opening is
   only possible because we have a clean slate without needing to re-use
   the ACC_MODE flag design nor the existing openat(2) @mode semantics.

To this end, we introduce the openat2(2) syscall. It provides all of the
features of openat(2) through the @how->flags argument, but also
also provides a new @how->resolve argument which exposes RESOLVE_* flags
that map to our new LOOKUP_* flags. It also eliminates the long-standing
ugliness of variadic-open(2) by embedding it in a struct.

In order to allow for userspace to lock down their usage of file
descriptor re-opening, openat2(2) has the ability for users to disallow
certain re-opening modes through @how->upgrade_mask. At the moment,
there is no UPGRADE_NOEXEC. The open_how struct is padded to 64 bytes
for future extensions (all of the reserved bits must be zeroed).

[1]: https://github.com/openSUSE/libpathrs

Suggested-by: Christian Brauner <christian@brauner.io>
Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
---
 arch/alpha/kernel/syscalls/syscall.tbl      |   1 +
 arch/arm/tools/syscall.tbl                  |   1 +
 arch/arm64/include/asm/unistd.h             |   2 +-
 arch/arm64/include/asm/unistd32.h           |   2 +
 arch/ia64/kernel/syscalls/syscall.tbl       |   1 +
 arch/m68k/kernel/syscalls/syscall.tbl       |   1 +
 arch/microblaze/kernel/syscalls/syscall.tbl |   1 +
 arch/mips/kernel/syscalls/syscall_n32.tbl   |   1 +
 arch/mips/kernel/syscalls/syscall_n64.tbl   |   1 +
 arch/mips/kernel/syscalls/syscall_o32.tbl   |   1 +
 arch/parisc/kernel/syscalls/syscall.tbl     |   1 +
 arch/powerpc/kernel/syscalls/syscall.tbl    |   1 +
 arch/s390/kernel/syscalls/syscall.tbl       |   1 +
 arch/sh/kernel/syscalls/syscall.tbl         |   1 +
 arch/sparc/kernel/syscalls/syscall.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_32.tbl      |   1 +
 arch/x86/entry/syscalls/syscall_64.tbl      |   1 +
 arch/xtensa/kernel/syscalls/syscall.tbl     |   1 +
 fs/open.c                                   | 106 ++++++++++++++++----
 include/linux/fcntl.h                       |  15 ++-
 include/linux/fs.h                          |   4 +-
 include/linux/syscalls.h                    |  17 +++-
 include/uapi/asm-generic/unistd.h           |   5 +-
 include/uapi/linux/fcntl.h                  |  42 ++++++++
 24 files changed, 179 insertions(+), 30 deletions(-)

diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 728fe028c02c..9f374f7d9514 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -475,3 +475,4 @@
 543	common	fspick				sys_fspick
 544	common	pidfd_open			sys_pidfd_open
 # 545 reserved for clone3
+547	common	openat2				sys_openat2
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 6da7dc4d79cc..4ba54bc7e19a 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -449,3 +449,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				sys_clone3
+437	common	openat2				sys_openat2
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 2629a68b8724..8aa00ccb0b96 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -38,7 +38,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		436
+#define __NR_compat_syscalls		438
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 94ab29cf4f00..57f6f592d460 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -879,6 +879,8 @@ __SYSCALL(__NR_fspick, sys_fspick)
 __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
 #define __NR_clone3 435
 __SYSCALL(__NR_clone3, sys_clone3)
+#define __NR_openat2 437
+__SYSCALL(__NR_openat2, sys_openat2)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 36d5faf4c86c..8d36f2e2dc89 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -356,3 +356,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
+437	common	openat2				sys_openat2
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index a88a285a0e5f..2559925f1924 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -435,3 +435,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
+437	common	openat2				sys_openat2
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 09b0cd7dab0a..c04385e60833 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -441,3 +441,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				sys_clone3
+437	common	openat2				sys_openat2
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index c9c879ec9b6d..ba06cae655c6 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -374,3 +374,4 @@
 433	n32	fspick				sys_fspick
 434	n32	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
+437	n32	openat2				sys_openat2
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index bbce9159caa1..0f3de320ae51 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -350,3 +350,4 @@
 433	n64	fspick				sys_fspick
 434	n64	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
+437	n64	openat2				sys_openat2
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 9653591428ec..f108464d09a3 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -423,3 +423,4 @@
 433	o32	fspick				sys_fspick
 434	o32	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
+437	o32	openat2				sys_openat2			sys_openat2
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 670d1371aca1..45ddc4485844 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -432,3 +432,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				sys_clone3_wrapper
+437	common	openat2				sys_openat2
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 43f736ed47f2..a8b5ecb5b602 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -517,3 +517,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	nospu	clone3				ppc_clone3
+437	common	openat2				sys_openat2
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 3054e9c035a3..16b571c06161 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -438,3 +438,4 @@
 433  common	fspick			sys_fspick			sys_fspick
 434  common	pidfd_open		sys_pidfd_open			sys_pidfd_open
 435  common	clone3			sys_clone3			sys_clone3
+437  common	openat2			sys_openat2			sys_openat2
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index b5ed26c4c005..a7185cc18626 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -438,3 +438,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
+437	common	openat2				sys_openat2
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 8c8cc7537fb2..b11c19552022 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -481,3 +481,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
+437	common	openat2			sys_openat2
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index c00019abd076..dfa1dc5c8587 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -440,3 +440,4 @@
 433	i386	fspick			sys_fspick			__ia32_sys_fspick
 434	i386	pidfd_open		sys_pidfd_open			__ia32_sys_pidfd_open
 435	i386	clone3			sys_clone3			__ia32_sys_clone3
+437	i386	openat2			sys_openat2			__ia32_sys_openat2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index c29976eca4a8..9035647ef236 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -357,6 +357,7 @@
 433	common	fspick			__x64_sys_fspick
 434	common	pidfd_open		__x64_sys_pidfd_open
 435	common	clone3			__x64_sys_clone3/ptregs
+437	common	openat2			__x64_sys_openat2
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 25f4de729a6d..f0a68013c038 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -406,3 +406,4 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				sys_clone3
+437	common	openat2				sys_openat2
diff --git a/fs/open.c b/fs/open.c
index 310b896eecf0..0f050b5e6921 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -947,19 +947,29 @@ struct file *open_with_fake_path(const struct path *path, int flags,
 }
 EXPORT_SYMBOL(open_with_fake_path);
 
-static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
+static inline int build_open_flags(const struct open_how *how,
+				   struct open_flags *op)
 {
+	int flags = how->flags;
 	int lookup_flags = 0;
+	int opath_mask = 0;
 	int acc_mode = ACC_MODE(flags);
 
 	/*
-	 * Clear out all open flags we don't know about so that we don't report
-	 * them in fcntl(F_GETFD) or similar interfaces.
+	 * Older syscalls still clear these bits before calling
+	 * build_open_flags(), but openat2(2) checks all its arguments.
 	 */
-	flags &= VALID_OPEN_FLAGS;
+	if (flags & ~VALID_OPEN_FLAGS)
+		return -EINVAL;
+	if (how->resolve & ~VALID_RESOLVE_FLAGS)
+		return -EINVAL;
+	if (!(how->flags & (O_PATH | O_CREAT | __O_TMPFILE)) && how->mode != 0)
+		return -EINVAL;
+	if (memchr_inv(how->reserved, 0, sizeof(how->reserved)))
+		return -EINVAL;
 
 	if (flags & (O_CREAT | __O_TMPFILE))
-		op->mode = (mode & S_IALLUGO) | S_IFREG;
+		op->mode = (how->mode & S_IALLUGO) | S_IFREG;
 	else
 		op->mode = 0;
 
@@ -987,6 +997,14 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 		 */
 		flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
 		acc_mode = 0;
+
+		/* Allow userspace to restrict the re-opening of O_PATH fds. */
+		if (how->upgrade_mask & ~VALID_UPGRADE_FLAGS)
+			return -EINVAL;
+		if (!(how->upgrade_mask & UPGRADE_NOREAD))
+			opath_mask |= FMODE_PATH_READ;
+		if (!(how->upgrade_mask & UPGRADE_NOWRITE))
+			opath_mask |= FMODE_PATH_WRITE;
 	}
 
 	op->open_flag = flags;
@@ -1002,8 +1020,7 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 
 	op->acc_mode = acc_mode;
 	op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
-	/* For O_PATH backwards-compatibility we default to an all-set mask. */
-	op->opath_mask = FMODE_PATH_READ | FMODE_PATH_WRITE;
+	op->opath_mask = opath_mask;
 
 	if (flags & O_CREAT) {
 		op->intent |= LOOKUP_CREATE;
@@ -1017,6 +1034,18 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 		lookup_flags |= LOOKUP_FOLLOW;
 	if (flags & O_EMPTYPATH)
 		lookup_flags |= LOOKUP_EMPTY;
+
+	if (how->resolve & RESOLVE_NO_XDEV)
+		lookup_flags |= LOOKUP_NO_XDEV;
+	if (how->resolve & RESOLVE_NO_MAGICLINKS)
+		lookup_flags |= LOOKUP_NO_MAGICLINKS;
+	if (how->resolve & RESOLVE_NO_SYMLINKS)
+		lookup_flags |= LOOKUP_NO_SYMLINKS;
+	if (how->resolve & RESOLVE_BENEATH)
+		lookup_flags |= LOOKUP_BENEATH;
+	if (how->resolve & RESOLVE_IN_ROOT)
+		lookup_flags |= LOOKUP_IN_ROOT;
+
 	op->lookup_flags = lookup_flags;
 	return 0;
 }
@@ -1035,8 +1064,14 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 struct file *file_open_name(struct filename *name, int flags, umode_t mode)
 {
 	struct open_flags op;
-	int err = build_open_flags(flags, mode, &op);
-	return err ? ERR_PTR(err) : do_filp_open(AT_FDCWD, name, &op);
+	struct open_how how = {
+		.flags = flags & VALID_OPEN_FLAGS,
+		.mode = OPENHOW_MODE(flags, mode),
+	};
+	int err = build_open_flags(&how, &op);
+	if (err)
+		return ERR_PTR(err);
+	return do_filp_open(AT_FDCWD, name, &op);
 }
 
 /**
@@ -1067,17 +1102,22 @@ struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 			    const char *filename, int flags, umode_t mode)
 {
 	struct open_flags op;
-	int err = build_open_flags(flags, mode, &op);
+	struct open_how how = {
+		.flags = flags & VALID_OPEN_FLAGS,
+		.mode = OPENHOW_MODE(flags, mode),
+	};
+	int err = build_open_flags(&how, &op);
 	if (err)
 		return ERR_PTR(err);
 	return do_file_open_root(dentry, mnt, filename, &op);
 }
 EXPORT_SYMBOL(file_open_root);
 
-long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
+long do_sys_open(int dfd, const char __user *filename,
+		 struct open_how *how)
 {
 	struct open_flags op;
-	int fd = build_open_flags(flags, mode, &op);
+	int fd = build_open_flags(how, &op);
 	int empty = 0;
 	struct filename *tmp;
 
@@ -1090,7 +1130,7 @@ long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
 	if (!empty)
 		op.open_flag &= ~O_EMPTYPATH;
 
-	fd = get_unused_fd_flags(flags);
+	fd = get_unused_fd_flags(how->flags);
 	if (fd >= 0) {
 		struct file *f = do_filp_open(dfd, tmp, &op);
 		if (IS_ERR(f)) {
@@ -1107,19 +1147,35 @@ long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
 
 SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
 {
-	if (force_o_largefile())
-		flags |= O_LARGEFILE;
-
-	return do_sys_open(AT_FDCWD, filename, flags, mode);
+	return ksys_open(filename, flags, mode);
 }
 
 SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
 		umode_t, mode)
 {
+	struct open_how how = {
+		.flags = flags & VALID_OPEN_FLAGS,
+		.mode = OPENHOW_MODE(flags, mode),
+	};
+
+	if (force_o_largefile())
+		how.flags |= O_LARGEFILE;
+
+	return do_sys_open(dfd, filename, &how);
+}
+
+SYSCALL_DEFINE3(openat2, int, dfd, const char __user *, filename,
+		const struct open_how __user *, how)
+{
+	struct open_how tmp;
+
+	if (copy_from_user(&tmp, how, sizeof(tmp)))
+		return -EFAULT;
+
 	if (force_o_largefile())
-		flags |= O_LARGEFILE;
+		tmp.flags |= O_LARGEFILE;
 
-	return do_sys_open(dfd, filename, flags, mode);
+	return do_sys_open(dfd, filename, &tmp);
 }
 
 #ifdef CONFIG_COMPAT
@@ -1129,7 +1185,11 @@ SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
  */
 COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
 {
-	return do_sys_open(AT_FDCWD, filename, flags, mode);
+	struct open_how how = {
+		.flags = flags & VALID_OPEN_FLAGS,
+		.mode = OPENHOW_MODE(flags, mode),
+	};
+	return do_sys_open(AT_FDCWD, filename, &how);
 }
 
 /*
@@ -1138,7 +1198,11 @@ COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t,
  */
 COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode)
 {
-	return do_sys_open(dfd, filename, flags, mode);
+	struct open_how how = {
+		.flags = flags & VALID_OPEN_FLAGS,
+		.mode = OPENHOW_MODE(flags, mode),
+	};
+	return do_sys_open(dfd, filename, &how);
 }
 #endif
 
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index 2868ae6c8fc1..f7f378e1f43c 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -4,13 +4,26 @@
 
 #include <uapi/linux/fcntl.h>
 
-/* list of all valid flags for the open/openat flags argument: */
+/* Should open_how.mode be set for older syscalls wrappers? */
+#define OPENHOW_MODE(flags, mode) \
+	(((flags) & (O_CREAT | __O_TMPFILE)) ? (mode) : 0)
+
+/* List of all valid flags for the open/openat flags argument: */
 #define VALID_OPEN_FLAGS \
 	(O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | \
 	 O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \
 	 FASYNC	| O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \
 	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE | O_EMPTYPATH)
 
+/* List of all valid flags for the how->upgrade_mask argument: */
+#define VALID_UPGRADE_FLAGS \
+	(UPGRADE_NOWRITE | UPGRADE_NOREAD)
+
+/* List of all valid flags for the how->resolve argument: */
+#define VALID_RESOLVE_FLAGS \
+	(RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \
+	 RESOLVE_BENEATH | RESOLVE_IN_ROOT)
+
 #ifndef force_o_largefile
 #define force_o_largefile() (!IS_ENABLED(CONFIG_ARCH_32BIT_OFF_T))
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a9ad596b28e2..135e4fa773fc 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2498,8 +2498,8 @@ extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
 		       struct file *filp);
 extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
 			loff_t len);
-extern long do_sys_open(int dfd, const char __user *filename, int flags,
-			umode_t mode);
+extern long do_sys_open(int dfd, const char __user *filename,
+			struct open_how *how);
 extern struct file *file_open_name(struct filename *, int, umode_t);
 extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 88145da7d140..a4f2f135001e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -69,6 +69,7 @@ struct rseq;
 union bpf_attr;
 struct io_uring_params;
 struct clone_args;
+struct open_how;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -439,6 +440,8 @@ asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user,
 asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group);
 asmlinkage long sys_openat(int dfd, const char __user *filename, int flags,
 			   umode_t mode);
+asmlinkage long sys_openat2(int dfd, const char __user *filename,
+			    const struct open_how *how);
 asmlinkage long sys_close(unsigned int fd);
 asmlinkage long sys_vhangup(void);
 
@@ -1374,15 +1377,21 @@ static inline int ksys_close(unsigned int fd)
 	return __close_fd(current->files, fd);
 }
 
-extern long do_sys_open(int dfd, const char __user *filename, int flags,
-			umode_t mode);
+extern long do_sys_open(int dfd, const char __user *filename,
+			struct open_how *how);
 
 static inline long ksys_open(const char __user *filename, int flags,
 			     umode_t mode)
 {
+	struct open_how how = {
+		.flags = flags & VALID_OPEN_FLAGS,
+		.mode = OPENHOW_MODE(flags, mode),
+	};
+
 	if (force_o_largefile())
-		flags |= O_LARGEFILE;
-	return do_sys_open(AT_FDCWD, filename, flags, mode);
+		how.flags |= O_LARGEFILE;
+
+	return do_sys_open(AT_FDCWD, filename, &how);
 }
 
 extern long do_sys_truncate(const char __user *pathname, loff_t length);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 1be0e798e362..b28c11b338ee 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -851,8 +851,11 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
 __SYSCALL(__NR_clone3, sys_clone3)
 #endif
 
+#define __NR_openat2 437
+__SYSCALL(__NR_openat2, sys_openat2)
+
 #undef __NR_syscalls
-#define __NR_syscalls 436
+#define __NR_syscalls 438
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index 1d338357df8a..ebfc97b3d8aa 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -93,5 +93,47 @@
 
 #define AT_RECURSIVE		0x8000	/* Apply to the entire subtree */
 
+/**
+ * Arguments for how openat2(2) should open the target path. If @resolve is
+ * zero, then openat2(2) operates identically to openat(2).
+ *
+ * However, unlike openat(2), unknown bits in @flags result in -EINVAL rather
+ * than being silently ignored. In addition, @mode (or @upgrade_mask) must be
+ * zero unless one of {O_CREAT, O_TMPFILE, O_PATH} are set.
+ *
+ * @flags: O_* flags.
+ * @mode: O_CREAT/O_TMPFILE file mode.
+ * @upgrade_mask: UPGRADE_* flags (to restrict O_PATH re-opening).
+ * @resolve: RESOLVE_* flags.
+ * @reserved: reserved for future extensions, must be zeroed.
+ */
+struct open_how {
+	__u32 flags;
+	union {
+		__u16 mode;
+		__u16 upgrade_mask;
+	};
+	__u16 resolve;
+	__u64 reserved[7]; /* must be zeroed */
+};
+
+/* how->resolve flags for openat2(2). */
+#define RESOLVE_NO_XDEV		0x01 /* Block mount-point crossings
+					(includes bind-mounts). */
+#define RESOLVE_NO_MAGICLINKS	0x02 /* Block traversal through procfs-style
+					"magic-links". */
+#define RESOLVE_NO_SYMLINKS	0x04 /* Block traversal through all symlinks
+					(implies OEXT_NO_MAGICLINKS) */
+#define RESOLVE_BENEATH		0x08 /* Block "lexical" trickery like
+					"..", symlinks, and absolute
+					paths which escape the dirfd. */
+#define RESOLVE_IN_ROOT		0x10 /* Make all jumps to "/" and ".."
+					be scoped inside the dirfd
+					(similar to chroot(2)). */
+
+/* how->upgrade flags for openat2(2). */
+/* First bit is reserved for a future UPGRADE_NOEXEC flag. */
+#define UPGRADE_NOREAD		0x02 /* Block re-opening with MAY_READ. */
+#define UPGRADE_NOWRITE		0x04 /* Block re-opening with MAY_WRITE. */
 
 #endif /* _UAPI_LINUX_FCNTL_H */
-- 
2.22.0


^ permalink raw reply related

* [PATCH RESEND v11 3/8] open: O_EMPTYPATH: procfs-less file descriptor re-opening
From: Aleksa Sarai @ 2019-08-20  3:34 UTC (permalink / raw)
  To: Al Viro, Jeff Layton, J. Bruce Fields, Arnd Bergmann,
	David Howells, Shuah Khan, Shuah Khan
  Cc: linux-ia64, linux-sh, Alexei Starovoitov, Oleg Nesterov,
	linux-kselftest, sparclinux, linux-arch, linux-s390,
	Tycho Andersen, Aleksa Sarai, linux-arm-kernel, linux-mips,
	linux-xtensa, Kees Cook, Jann Horn, linuxppc-dev, Aleksa Sarai,
	Andy Lutomirski, David Drysdale, Christian Brauner, linux-parisc,
	linux-m68k, linux-api, Chanho Min, linux-kernel, Eric Biederman,
	linux-alpha, linux-fsdevel, Andrew Morton, Linus Torvalds,
	containers
In-Reply-To: <20190820033406.29796-1-cyphar@cyphar.com>

Userspace has made use of /proc/self/fd very liberally to allow for
descriptors to be re-opened. There are a wide variety of uses for this
feature, but it has always required constructing a pathname and could
not be done without procfs mounted. The obvious solution for this is to
extend openat(2) to have an AT_EMPTY_PATH-equivalent -- O_EMPTYPATH.

Now that descriptor re-opening has been made safe through the new
magic-link resolution restrictions, we can replicate these restrictions
for O_EMPTYPATH. In particular, we only allow "upgrading" the file
descriptor if the corresponding FMODE_PATH_* bit is set (or the
FMODE_{READ,WRITE} cases for non-O_PATH file descriptors).

When doing openat(O_EMPTYPATH|O_PATH), O_PATH takes precedence and
O_EMPTYPATH is ignored. Very few users ever have a need to O_PATH
re-open an existing file descriptor, and so accommodating them at the
expense of further complicating O_PATH makes little sense. Ultimately,
if users ask for this we can always add RESOLVE_EMPTY_PATH to
resolveat(2) in the future.

Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
---
 arch/alpha/include/uapi/asm/fcntl.h  |  1 +
 arch/parisc/include/uapi/asm/fcntl.h | 39 ++++++++++++++--------------
 arch/sparc/include/uapi/asm/fcntl.h  |  1 +
 fs/fcntl.c                           |  2 +-
 fs/namei.c                           | 20 ++++++++++++++
 fs/open.c                            |  7 ++++-
 include/linux/fcntl.h                |  2 +-
 include/uapi/asm-generic/fcntl.h     |  4 +++
 8 files changed, 54 insertions(+), 22 deletions(-)

diff --git a/arch/alpha/include/uapi/asm/fcntl.h b/arch/alpha/include/uapi/asm/fcntl.h
index 50bdc8e8a271..1f879bade68b 100644
--- a/arch/alpha/include/uapi/asm/fcntl.h
+++ b/arch/alpha/include/uapi/asm/fcntl.h
@@ -34,6 +34,7 @@
 
 #define O_PATH		040000000
 #define __O_TMPFILE	0100000000
+#define O_EMPTYPATH	0200000000
 
 #define F_GETLK		7
 #define F_SETLK		8
diff --git a/arch/parisc/include/uapi/asm/fcntl.h b/arch/parisc/include/uapi/asm/fcntl.h
index 03ce20e5ad7d..5d709058a76f 100644
--- a/arch/parisc/include/uapi/asm/fcntl.h
+++ b/arch/parisc/include/uapi/asm/fcntl.h
@@ -2,26 +2,27 @@
 #ifndef _PARISC_FCNTL_H
 #define _PARISC_FCNTL_H
 
-#define O_APPEND	000000010
-#define O_BLKSEEK	000000100 /* HPUX only */
-#define O_CREAT		000000400 /* not fcntl */
-#define O_EXCL		000002000 /* not fcntl */
-#define O_LARGEFILE	000004000
-#define __O_SYNC	000100000
+#define O_APPEND	0000000010
+#define O_BLKSEEK	0000000100 /* HPUX only */
+#define O_CREAT		0000000400 /* not fcntl */
+#define O_EXCL		0000002000 /* not fcntl */
+#define O_LARGEFILE	0000004000
+#define __O_SYNC	0000100000
 #define O_SYNC		(__O_SYNC|O_DSYNC)
-#define O_NONBLOCK	000200004 /* HPUX has separate NDELAY & NONBLOCK */
-#define O_NOCTTY	000400000 /* not fcntl */
-#define O_DSYNC		001000000 /* HPUX only */
-#define O_RSYNC		002000000 /* HPUX only */
-#define O_NOATIME	004000000
-#define O_CLOEXEC	010000000 /* set close_on_exec */
-
-#define O_DIRECTORY	000010000 /* must be a directory */
-#define O_NOFOLLOW	000000200 /* don't follow links */
-#define O_INVISIBLE	004000000 /* invisible I/O, for DMAPI/XDSM */
-
-#define O_PATH		020000000
-#define __O_TMPFILE	040000000
+#define O_NONBLOCK	0000200004 /* HPUX has separate NDELAY & NONBLOCK */
+#define O_NOCTTY	0000400000 /* not fcntl */
+#define O_DSYNC		0001000000 /* HPUX only */
+#define O_RSYNC		0002000000 /* HPUX only */
+#define O_NOATIME	0004000000
+#define O_CLOEXEC	0010000000 /* set close_on_exec */
+
+#define O_DIRECTORY	0000010000 /* must be a directory */
+#define O_NOFOLLOW	0000000200 /* don't follow links */
+#define O_INVISIBLE	0004000000 /* invisible I/O, for DMAPI/XDSM */
+
+#define O_PATH		0020000000
+#define __O_TMPFILE	0040000000
+#define O_EMPTYPATH	0100000000
 
 #define F_GETLK64	8
 #define F_SETLK64	9
diff --git a/arch/sparc/include/uapi/asm/fcntl.h b/arch/sparc/include/uapi/asm/fcntl.h
index 67dae75e5274..dc86c9eaf950 100644
--- a/arch/sparc/include/uapi/asm/fcntl.h
+++ b/arch/sparc/include/uapi/asm/fcntl.h
@@ -37,6 +37,7 @@
 
 #define O_PATH		0x1000000
 #define __O_TMPFILE	0x2000000
+#define O_EMPTYPATH	0x4000000
 
 #define F_GETOWN	5	/*  for sockets. */
 #define F_SETOWN	6	/*  for sockets. */
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 3d40771e8e7c..4cf05a2fd162 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -1031,7 +1031,7 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ !=
+	BUILD_BUG_ON(22 - 1 /* for O_RDONLY being 0 */ !=
 		HWEIGHT32(
 			(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
 			__FMODE_EXEC | __FMODE_NONOTIFY));
diff --git a/fs/namei.c b/fs/namei.c
index 54d57dad0f91..e39b573fcc4d 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3571,6 +3571,24 @@ static int trailing_magiclink(struct nameidata *nd, int acc_mode,
 	return may_open_magiclink(upgrade_mask, acc_mode);
 }
 
+static int do_emptypath(struct nameidata *nd, const struct open_flags *op,
+			struct file *file)
+{
+	int error;
+	/* We don't support AT_FDCWD (since O_PATH is disallowed here). */
+	struct fd f = fdget_raw(nd->dfd);
+
+	if (!f.file)
+		return -EBADF;
+
+	/* Apply trailing_magiclink()-like restrictions. */
+	error = may_open_magiclink(f.file->f_mode, op->acc_mode);
+	if (!error)
+		error = vfs_open(&f.file->f_path, file);
+	fdput(f);
+	return error;
+}
+
 static struct file *path_openat(struct nameidata *nd,
 			const struct open_flags *op, unsigned flags)
 {
@@ -3583,6 +3601,8 @@ static struct file *path_openat(struct nameidata *nd,
 
 	if (unlikely(file->f_flags & __O_TMPFILE)) {
 		error = do_tmpfile(nd, flags, op, file);
+	} else if (unlikely(file->f_flags & O_EMPTYPATH)) {
+		error = do_emptypath(nd, op, file);
 	} else if (unlikely(file->f_flags & O_PATH)) {
 		/* Inlined path_lookupat() with a trailing_magiclink() check. */
 		fmode_t opath_mask = op->opath_mask;
diff --git a/fs/open.c b/fs/open.c
index 806a75d685e1..310b896eecf0 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1015,6 +1015,8 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 		lookup_flags |= LOOKUP_DIRECTORY;
 	if (!(flags & O_NOFOLLOW))
 		lookup_flags |= LOOKUP_FOLLOW;
+	if (flags & O_EMPTYPATH)
+		lookup_flags |= LOOKUP_EMPTY;
 	op->lookup_flags = lookup_flags;
 	return 0;
 }
@@ -1076,14 +1078,17 @@ long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
 {
 	struct open_flags op;
 	int fd = build_open_flags(flags, mode, &op);
+	int empty = 0;
 	struct filename *tmp;
 
 	if (fd)
 		return fd;
 
-	tmp = getname(filename);
+	tmp = getname_flags(filename, op.lookup_flags, &empty);
 	if (IS_ERR(tmp))
 		return PTR_ERR(tmp);
+	if (!empty)
+		op.open_flag &= ~O_EMPTYPATH;
 
 	fd = get_unused_fd_flags(flags);
 	if (fd >= 0) {
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index d019df946cb2..2868ae6c8fc1 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -9,7 +9,7 @@
 	(O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | \
 	 O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \
 	 FASYNC	| O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \
-	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE)
+	 O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE | O_EMPTYPATH)
 
 #ifndef force_o_largefile
 #define force_o_largefile() (!IS_ENABLED(CONFIG_ARCH_32BIT_OFF_T))
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index 9dc0bf0c5a6e..ae6862f69cc2 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -89,6 +89,10 @@
 #define __O_TMPFILE	020000000
 #endif
 
+#ifndef O_EMPTYPATH
+#define O_EMPTYPATH 040000000
+#endif
+
 /* a horrid kludge trying to make sure that this will fail on old kernels */
 #define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
 #define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)      
-- 
2.22.0


^ permalink raw reply related

* [PATCH RESEND v11 4/8] namei: O_BENEATH-style path resolution flags
From: Aleksa Sarai @ 2019-08-20  3:34 UTC (permalink / raw)
  To: Al Viro, Jeff Layton, J. Bruce Fields, Arnd Bergmann,
	David Howells, Shuah Khan, Shuah Khan
  Cc: linux-ia64, linux-sh, Alexei Starovoitov, Oleg Nesterov,
	linux-kselftest, sparclinux, linux-arch, linux-s390,
	Tycho Andersen, Aleksa Sarai, linux-arm-kernel, linux-mips,
	linux-xtensa, Kees Cook, Jann Horn, linuxppc-dev, Aleksa Sarai,
	Andy Lutomirski, David Drysdale, Christian Brauner, linux-parisc,
	linux-m68k, linux-api, Chanho Min, linux-kernel, Eric Biederman,
	linux-alpha, linux-fsdevel, Andrew Morton, Linus Torvalds,
	containers
In-Reply-To: <20190820033406.29796-1-cyphar@cyphar.com>

Add the following flags to allow various restrictions on path resolution
(these affect the *entire* resolution, rather than just the final path
component -- as is the case with LOOKUP_FOLLOW).

The primary justification for these flags is to allow for programs to be
far more strict about how they want path resolution to handle symlinks,
mountpoint crossings, and paths that escape the dirfd (through an
absolute path or ".." shenanigans).

This is of particular concern to container runtimes that want to be very
careful about malicious root filesystems that a container's init might
have screwed around with (and there is no real way to protect against
this in userspace if you consider potential races against a malicious
container's init). More classical applications (which have their own
potentially buggy userspace path sanitisation code) include web servers,
archive extraction tools, network file servers, and so on.

These flags are exposed to userspace through openat2(2) in a later
patchset.

* LOOKUP_NO_XDEV: Disallow mount-point crossing (both *down* into one,
  or *up* from one). Both bind-mounts and cross-filesystem mounts are
  blocked by this flag. The naming is based on "find -xdev" as well as
  -EXDEV (though find(1) doesn't walk upwards, the semantics seem
  obvious).

* LOOKUP_NO_MAGICLINKS: Disallows ->get_link "symlink" (or rather,
  magic-link) jumping. This is a very specific restriction, and it
  exists because /proc/$pid/fd/... "symlinks" allow for access outside
  nd->root and pose risk to container runtimes that don't want to be
  tricked into accessing a host path (but do want to allow
  no-funny-business symlink resolution).

* LOOKUP_NO_SYMLINKS: Disallows resolution through symlinks of any kind
  (including magic-links).

* LOOKUP_BENEATH: Disallow "escapes" from the starting point of the
  filesystem tree during resolution (you must stay "beneath" the
  starting point at all times). Currently this is done by disallowing
  ".." and absolute paths (either in the given path or found during
  symlink resolution) entirely, as well as all magic-link jumping.

  The wholesale banning of ".." is because it is currently not safe to
  allow ".." resolution (races can cause the path to be moved outside of
  the root -- this is conceptually similar to historical chroot(2)
  escape attacks). Future patches in this series will address this, and
  will re-enable ".." resolution once it is safe. With those patches,
  ".." resolution will only be allowed if it remains in the root
  throughout resolution (such as "a/../b" not "a/../../outside/b").

  The banning of magic-link jumping is done because it is not clear
  whether semantically they should be allowed -- while some magic-links
  are safe there are many that can cause escapes (and once a
  resolution is outside of the root, O_BENEATH will no longer detect
  it). Future patches may re-enable magic-link jumping when such jumps
  would remain inside the root.

The LOOKUP_NO_*LINK flags return -ELOOP if path resolution would
violates their requirement, while the others all return -EXDEV.

This is a refresh of Al's AT_NO_JUMPS patchset[1] (which was a variation
on David Drysdale's O_BENEATH patchset[2], which in turn was based on
the Capsicum project[3]). Input from Linus and Andy in the AT_NO_JUMPS
thread[4] determined most of the API changes made in this refresh.

[1]: https://lwn.net/Articles/721443/
[2]: https://lwn.net/Articles/619151/
[3]: https://lwn.net/Articles/603929/
[4]: https://lwn.net/Articles/723057/

Cc: Christian Brauner <christian@brauner.io>
Suggested-by: David Drysdale <drysdale@google.com>
Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Suggested-by: Andy Lutomirski <luto@kernel.org>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
---
 fs/namei.c            | 85 ++++++++++++++++++++++++++++++++++++-------
 include/linux/namei.h |  7 ++++
 2 files changed, 78 insertions(+), 14 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index e39b573fcc4d..2e18ce5a313e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -674,7 +674,11 @@ static int unlazy_walk(struct nameidata *nd)
 		goto out2;
 	if (unlikely(!legitimize_path(nd, &nd->path, nd->seq)))
 		goto out1;
-	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+	if (!nd->root.mnt) {
+		/* Restart from path_init() if nd->root was cleared. */
+		if (nd->flags & LOOKUP_BENEATH)
+			goto out;
+	} else if (!(nd->flags & LOOKUP_ROOT)) {
 		if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq)))
 			goto out;
 	}
@@ -843,6 +847,13 @@ static inline void path_to_nameidata(const struct path *path,
 
 static int nd_jump_root(struct nameidata *nd)
 {
+	if (unlikely(nd->flags & LOOKUP_BENEATH))
+		return -EXDEV;
+	if (unlikely(nd->flags & LOOKUP_NO_XDEV)) {
+		/* Absolute path arguments to path_init() are allowed. */
+		if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt)
+			return -EXDEV;
+	}
 	if (nd->flags & LOOKUP_RCU) {
 		struct dentry *d;
 		nd->path = nd->root;
@@ -1051,6 +1062,9 @@ const char *get_link(struct nameidata *nd)
 	int error;
 	const char *res;
 
+	if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS))
+		return ERR_PTR(-ELOOP);
+
 	if (!(nd->flags & LOOKUP_RCU)) {
 		touch_atime(&last->link);
 		cond_resched();
@@ -1082,14 +1096,22 @@ const char *get_link(struct nameidata *nd)
 		} else {
 			res = get(dentry, inode, &last->done);
 		}
+		if (nd->flags & LOOKUP_MAGICLINK_JUMPED) {
+			if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS))
+				return ERR_PTR(-ELOOP);
+			/* Not currently safe. */
+			if (unlikely(nd->flags & LOOKUP_BENEATH))
+				return ERR_PTR(-EXDEV);
+		}
 		if (IS_ERR_OR_NULL(res))
 			return res;
 	}
 	if (*res == '/') {
 		if (!nd->root.mnt)
 			set_root(nd);
-		if (unlikely(nd_jump_root(nd)))
-			return ERR_PTR(-ECHILD);
+		error = nd_jump_root(nd);
+		if (unlikely(error))
+			return ERR_PTR(error);
 		while (unlikely(*++res == '/'))
 			;
 	}
@@ -1270,12 +1292,16 @@ static int follow_managed(struct path *path, struct nameidata *nd)
 		break;
 	}
 
-	if (need_mntput && path->mnt == mnt)
-		mntput(path->mnt);
+	if (need_mntput) {
+		if (path->mnt == mnt)
+			mntput(path->mnt);
+		if (unlikely(nd->flags & LOOKUP_NO_XDEV))
+			ret = -EXDEV;
+		else
+			nd->flags |= LOOKUP_JUMPED;
+	}
 	if (ret == -EISDIR || !ret)
 		ret = 1;
-	if (need_mntput)
-		nd->flags |= LOOKUP_JUMPED;
 	if (unlikely(ret < 0))
 		path_put_conditional(path, nd);
 	return ret;
@@ -1332,6 +1358,8 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 		mounted = __lookup_mnt(path->mnt, path->dentry);
 		if (!mounted)
 			break;
+		if (unlikely(nd->flags & LOOKUP_NO_XDEV))
+			return false;
 		path->mnt = &mounted->mnt;
 		path->dentry = mounted->mnt.mnt_root;
 		nd->flags |= LOOKUP_JUMPED;
@@ -1352,8 +1380,11 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 	struct inode *inode = nd->inode;
 
 	while (1) {
-		if (path_equal(&nd->path, &nd->root))
+		if (path_equal(&nd->path, &nd->root)) {
+			if (unlikely(nd->flags & LOOKUP_BENEATH))
+				return -EXDEV;
 			break;
+		}
 		if (nd->path.dentry != nd->path.mnt->mnt_root) {
 			struct dentry *old = nd->path.dentry;
 			struct dentry *parent = old->d_parent;
@@ -1378,6 +1409,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 				return -ECHILD;
 			if (&mparent->mnt == nd->path.mnt)
 				break;
+			if (unlikely(nd->flags & LOOKUP_NO_XDEV))
+				return -EXDEV;
 			/* we know that mountpoint was pinned */
 			nd->path.dentry = mountpoint;
 			nd->path.mnt = &mparent->mnt;
@@ -1392,6 +1425,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 			return -ECHILD;
 		if (!mounted)
 			break;
+		if (unlikely(nd->flags & LOOKUP_NO_XDEV))
+			return -EXDEV;
 		nd->path.mnt = &mounted->mnt;
 		nd->path.dentry = mounted->mnt.mnt_root;
 		inode = nd->path.dentry->d_inode;
@@ -1480,8 +1515,11 @@ static int path_parent_directory(struct path *path)
 static int follow_dotdot(struct nameidata *nd)
 {
 	while(1) {
-		if (path_equal(&nd->path, &nd->root))
+		if (path_equal(&nd->path, &nd->root)) {
+			if (unlikely(nd->flags & LOOKUP_BENEATH))
+				return -EXDEV;
 			break;
+		}
 		if (nd->path.dentry != nd->path.mnt->mnt_root) {
 			int ret = path_parent_directory(&nd->path);
 			if (ret)
@@ -1490,6 +1528,8 @@ static int follow_dotdot(struct nameidata *nd)
 		}
 		if (!follow_up(&nd->path))
 			break;
+		if (unlikely(nd->flags & LOOKUP_NO_XDEV))
+			return -EXDEV;
 	}
 	follow_mount(&nd->path);
 	nd->inode = nd->path.dentry->d_inode;
@@ -1704,6 +1744,13 @@ static inline int may_lookup(struct nameidata *nd)
 static inline int handle_dots(struct nameidata *nd, int type)
 {
 	if (type == LAST_DOTDOT) {
+		/*
+		 * LOOKUP_BENEATH resolving ".." is not currently safe -- races
+		 * can cause our parent to have moved outside of the root and
+		 * us to skip over it.
+		 */
+		if (unlikely(nd->flags & LOOKUP_BENEATH))
+			return -EXDEV;
 		if (!nd->root.mnt)
 			set_root(nd);
 		if (nd->flags & LOOKUP_RCU) {
@@ -2170,6 +2217,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 /* must be paired with terminate_walk() */
 static const char *path_init(struct nameidata *nd, unsigned flags)
 {
+	int error;
 	const char *s = nd->name->name;
 
 	if (!*s)
@@ -2202,11 +2250,13 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	nd->path.dentry = NULL;
 
 	nd->m_seq = read_seqbegin(&mount_lock);
+
+	/* Figure out the starting path and root (if needed). */
 	if (*s == '/') {
 		set_root(nd);
-		if (likely(!nd_jump_root(nd)))
-			return s;
-		return ERR_PTR(-ECHILD);
+		error = nd_jump_root(nd);
+		if (unlikely(error))
+			return ERR_PTR(error);
 	} else if (nd->dfd == AT_FDCWD) {
 		if (flags & LOOKUP_RCU) {
 			struct fs_struct *fs = current->fs;
@@ -2222,7 +2272,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 			get_fs_pwd(current->fs, &nd->path);
 			nd->inode = nd->path.dentry->d_inode;
 		}
-		return s;
 	} else {
 		/* Caller must check execute permissions on the starting path component */
 		struct fd f = fdget_raw(nd->dfd);
@@ -2247,8 +2296,16 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 			nd->inode = nd->path.dentry->d_inode;
 		}
 		fdput(f);
-		return s;
 	}
+	/* For scoped-lookups we need to set the root to the dirfd as well. */
+	if (flags & LOOKUP_BENEATH) {
+		nd->root = nd->path;
+		if (flags & LOOKUP_RCU)
+			nd->root_seq = nd->seq;
+		else
+			path_get(&nd->root);
+	}
+	return s;
 }
 
 static const char *trailing_symlink(struct nameidata *nd)
diff --git a/include/linux/namei.h b/include/linux/namei.h
index bd6d3eb7764d..be407415c28a 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -51,6 +51,13 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_DOWN		0x8000
 #define LOOKUP_MAGICLINK_JUMPED	0x10000
 
+/* Scoping flags for lookup. */
+#define LOOKUP_BENEATH		0x020000 /* No escaping from starting point. */
+#define LOOKUP_NO_XDEV		0x040000 /* No mountpoint crossing. */
+#define LOOKUP_NO_MAGICLINKS	0x080000 /* No /proc/$pid/fd/ "symlink" crossing. */
+#define LOOKUP_NO_SYMLINKS	0x100000 /* No symlink crossing *at all*.
+					    Implies LOOKUP_NO_MAGICLINKS. */
+
 extern int path_pts(struct path *path);
 
 extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty);
-- 
2.22.0


^ permalink raw reply related

* [PATCH RESEND v11 5/8] namei: LOOKUP_IN_ROOT: chroot-like path resolution
From: Aleksa Sarai @ 2019-08-20  3:34 UTC (permalink / raw)
  To: Al Viro, Jeff Layton, J. Bruce Fields, Arnd Bergmann,
	David Howells, Shuah Khan, Shuah Khan
  Cc: linux-ia64, linux-sh, Alexei Starovoitov, Oleg Nesterov,
	linux-kselftest, sparclinux, linux-arch, linux-s390,
	Tycho Andersen, Aleksa Sarai, linux-arm-kernel, linux-mips,
	linux-xtensa, Kees Cook, Jann Horn, linuxppc-dev, Aleksa Sarai,
	Andy Lutomirski, David Drysdale, Christian Brauner, linux-parisc,
	linux-m68k, linux-api, Chanho Min, linux-kernel, Eric Biederman,
	linux-alpha, linux-fsdevel, Andrew Morton, Linus Torvalds,
	containers
In-Reply-To: <20190820033406.29796-1-cyphar@cyphar.com>

The primary motivation for the need for this flag is container runtimes
which have to interact with malicious root filesystems in the host
namespaces. One of the first requirements for a container runtime to be
secure against a malicious rootfs is that they correctly scope symlinks
(that is, they should be scoped as though they are chroot(2)ed into the
container's rootfs) and ".."-style paths[*]. The already-existing
LOOKUP_NO_XDEV and LOOKUP_NO_MAGICLINKS help defend against other
potential attacks in a malicious rootfs scenario.

Currently most container runtimes try to do this resolution in
userspace[1], causing many potential race conditions. In addition, the
"obvious" alternative (actually performing a {ch,pivot_}root(2))
requires a fork+exec (for some runtimes) which is *very* costly if
necessary for every filesystem operation involving a container.

[*] At the moment, ".." and magic-link jumping are disallowed for the
    same reason it is disabled for LOOKUP_BENEATH -- currently it is not
    safe to allow it. Future patches may enable it unconditionally once
    we have resolved the possible races (for "..") and semantics (for
    magic-link jumping).

The most significant *at(2) semantic change with LOOKUP_IN_ROOT is that
absolute pathnames no longer cause the dirfd to be ignored completely.

The rationale is that LOOKUP_IN_ROOT must necessarily chroot-scope
symlinks with absolute paths to dirfd, and so doing it for the base path
seems to be the most consistent behaviour (and also avoids foot-gunning
users who want to scope paths that are absolute).

[1]: https://github.com/cyphar/filepath-securejoin

Suggested-by: Christian Brauner <christian@brauner.io>
Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
---
 fs/namei.c            | 41 +++++++++++++++++++++++++++++++----------
 include/linux/namei.h |  1 +
 2 files changed, 32 insertions(+), 10 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 2e18ce5a313e..0352d275bd13 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -676,7 +676,7 @@ static int unlazy_walk(struct nameidata *nd)
 		goto out1;
 	if (!nd->root.mnt) {
 		/* Restart from path_init() if nd->root was cleared. */
-		if (nd->flags & LOOKUP_BENEATH)
+		if (nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT))
 			goto out;
 	} else if (!(nd->flags & LOOKUP_ROOT)) {
 		if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq)))
@@ -809,10 +809,18 @@ static int complete_walk(struct nameidata *nd)
 	return status;
 }
 
-static void set_root(struct nameidata *nd)
+static int set_root(struct nameidata *nd)
 {
 	struct fs_struct *fs = current->fs;
 
+	/*
+	 * Jumping to the real root as part of LOOKUP_IN_ROOT is a BUG in namei,
+	 * but we still have to ensure it doesn't happen because it will cause a
+	 * breakout from the dirfd.
+	 */
+	if (WARN_ON(nd->flags & LOOKUP_IN_ROOT))
+		return -ENOTRECOVERABLE;
+
 	if (nd->flags & LOOKUP_RCU) {
 		unsigned seq;
 
@@ -824,6 +832,7 @@ static void set_root(struct nameidata *nd)
 	} else {
 		get_fs_root(fs, &nd->root);
 	}
+	return 0;
 }
 
 static void path_put_conditional(struct path *path, struct nameidata *nd)
@@ -854,6 +863,11 @@ static int nd_jump_root(struct nameidata *nd)
 		if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt)
 			return -EXDEV;
 	}
+	if (!nd->root.mnt) {
+		int error = set_root(nd);
+		if (error)
+			return error;
+	}
 	if (nd->flags & LOOKUP_RCU) {
 		struct dentry *d;
 		nd->path = nd->root;
@@ -1100,15 +1114,13 @@ const char *get_link(struct nameidata *nd)
 			if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS))
 				return ERR_PTR(-ELOOP);
 			/* Not currently safe. */
-			if (unlikely(nd->flags & LOOKUP_BENEATH))
+			if (unlikely(nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT)))
 				return ERR_PTR(-EXDEV);
 		}
 		if (IS_ERR_OR_NULL(res))
 			return res;
 	}
 	if (*res == '/') {
-		if (!nd->root.mnt)
-			set_root(nd);
 		error = nd_jump_root(nd);
 		if (unlikely(error))
 			return ERR_PTR(error);
@@ -1744,15 +1756,20 @@ static inline int may_lookup(struct nameidata *nd)
 static inline int handle_dots(struct nameidata *nd, int type)
 {
 	if (type == LAST_DOTDOT) {
+		int error = 0;
+
 		/*
 		 * LOOKUP_BENEATH resolving ".." is not currently safe -- races
 		 * can cause our parent to have moved outside of the root and
 		 * us to skip over it.
 		 */
-		if (unlikely(nd->flags & LOOKUP_BENEATH))
+		if (unlikely(nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT)))
 			return -EXDEV;
-		if (!nd->root.mnt)
-			set_root(nd);
+		if (!nd->root.mnt) {
+			error = set_root(nd);
+			if (error)
+				return error;
+		}
 		if (nd->flags & LOOKUP_RCU) {
 			return follow_dotdot_rcu(nd);
 		} else
@@ -2251,9 +2268,13 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 
 	nd->m_seq = read_seqbegin(&mount_lock);
 
+	/* LOOKUP_IN_ROOT treats absolute paths as being relative-to-dirfd. */
+	if (flags & LOOKUP_IN_ROOT)
+		while (*s == '/')
+			s++;
+
 	/* Figure out the starting path and root (if needed). */
 	if (*s == '/') {
-		set_root(nd);
 		error = nd_jump_root(nd);
 		if (unlikely(error))
 			return ERR_PTR(error);
@@ -2298,7 +2319,7 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 		fdput(f);
 	}
 	/* For scoped-lookups we need to set the root to the dirfd as well. */
-	if (flags & LOOKUP_BENEATH) {
+	if (flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT)) {
 		nd->root = nd->path;
 		if (flags & LOOKUP_RCU)
 			nd->root_seq = nd->seq;
diff --git a/include/linux/namei.h b/include/linux/namei.h
index be407415c28a..ec2c6c588ea7 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -57,6 +57,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_NO_MAGICLINKS	0x080000 /* No /proc/$pid/fd/ "symlink" crossing. */
 #define LOOKUP_NO_SYMLINKS	0x100000 /* No symlink crossing *at all*.
 					    Implies LOOKUP_NO_MAGICLINKS. */
+#define LOOKUP_IN_ROOT		0x200000 /* Treat dirfd as %current->fs->root. */
 
 extern int path_pts(struct path *path);
 
-- 
2.22.0


^ permalink raw reply related

* [PATCH RESEND v11 6/8] namei: aggressively check for nd->root escape on ".." resolution
From: Aleksa Sarai @ 2019-08-20  3:34 UTC (permalink / raw)
  To: Al Viro, Jeff Layton, J. Bruce Fields, Arnd Bergmann,
	David Howells, Shuah Khan, Shuah Khan
  Cc: linux-ia64, linux-sh, Alexei Starovoitov, Oleg Nesterov,
	linux-kselftest, sparclinux, linux-arch, linux-s390,
	Tycho Andersen, Aleksa Sarai, linux-arm-kernel, linux-mips,
	linux-xtensa, Kees Cook, Jann Horn, linuxppc-dev, Aleksa Sarai,
	Andy Lutomirski, David Drysdale, Christian Brauner, linux-parisc,
	linux-m68k, linux-api, Chanho Min, linux-kernel, Eric Biederman,
	linux-alpha, linux-fsdevel, Andrew Morton, Linus Torvalds,
	containers
In-Reply-To: <20190820033406.29796-1-cyphar@cyphar.com>

This patch allows for LOOKUP_BENEATH and LOOKUP_IN_ROOT to safely permit
".." resolution (in the case of LOOKUP_BENEATH the resolution will still
fail if ".." resolution would resolve a path outside of the root --
while LOOKUP_IN_ROOT will chroot(2)-style scope it). Magic-link jumps
are still disallowed entirely because now they could result in
inconsistent behaviour if resolution encounters a subsequent ".."[*].

The need for this patch is explained by observing there is a fairly
easy-to-exploit race condition with chroot(2) (and thus by extension
LOOKUP_IN_ROOT and LOOKUP_BENEATH if ".." is allowed) where a rename(2)
of a path can be used to "skip over" nd->root and thus escape to the
filesystem above nd->root.

  thread1 [attacker]:
    for (;;)
      renameat2(AT_FDCWD, "/a/b/c", AT_FDCWD, "/a/d", RENAME_EXCHANGE);
  thread2 [victim]:
    for (;;)
      openat2(dirb, "b/c/../../etc/shadow",
              { .flags = O_PATH, .resolve = RESOLVE_IN_ROOT } );

With fairly significant regularity, thread2 will resolve to
"/etc/shadow" rather than "/a/b/etc/shadow". There is also a similar
(though somewhat more privileged) attack using MS_MOVE.

With this patch, such cases will be detected *during* ".." resolution
(which is the weak point of chroot(2) -- since walking *into* a
subdirectory tautologically cannot result in you walking *outside*
nd->root -- except through a bind-mount or magic-link). By detecting
this at ".." resolution (rather than checking only at the end of the
entire resolution) we can both correct escapes by jumping back to the
root (in the case of LOOKUP_IN_ROOT), as well as avoid revealing to
attackers the structure of the filesystem outside of the root (through
timing attacks for instance).

In order to avoid a quadratic lookup with each ".." entry, we only
activate the slow path if a write through &rename_lock or &mount_lock
has occurred during path resolution (&rename_lock and &mount_lock are
re-taken to further optimise the lookup). Since the primary attack being
protected against is MS_MOVE or rename(2), not doing additional checks
unless a mount or rename have occurred avoids making the common case
slow.

The use of path_is_under() here might seem suspect, but on further
inspection of the most important race (a path was *inside* the root but
is now *outside*), there appears to be no attack potential:

  * If path_is_under() occurs before the rename, then the path will be
    resolved -- however the path was originally inside the root and thus
    there is no escape (and to userspace it'd look like the rename
    occurred after the path was resolved). If path_is_under() occurs
    afterwards, the resolution is blocked.

  * Subsequent ".." jumps are guaranteed to check path_is_under() -- by
    construction, &rename_lock or &mount_lock must have been taken by
    the attacker after path_is_under() returned in the victim. Thus ".."
    will not be able to escape from the previously-inside-root path.

  * Walking down in the moved path is still safe since the entire
    subtree was moved (either by rename(2) or MS_MOVE) and because (as
    discussed above) walking down is safe.

A variant of the above attack is included in the selftests for
openat2(2) later in this patch series. I've run this test on several
machines for several days and no instances of a breakout were detected.
While this is not concrete proof that this is safe, when combined with
the above argument it should lend some trustworthiness to this
construction.

[*] It may be acceptable in the future to do a path_is_under() check
    after resolving a magic-link and permit resolution if the
    nd_jump_link() result is still within the dirfd. However this seems
    unlikely to be a feature that people *really* need* -- it can be
    added later if it turns out a lot of people want it.

Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Jann Horn <jannh@google.com>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
---
 fs/namei.c | 45 +++++++++++++++++++++++++++++++--------------
 1 file changed, 31 insertions(+), 14 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 0352d275bd13..fd1eb5ce8baa 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -491,7 +491,7 @@ struct nameidata {
 	struct path	root;
 	struct inode	*inode; /* path.dentry.d_inode */
 	unsigned int	flags;
-	unsigned	seq, m_seq;
+	unsigned	seq, m_seq, r_seq;
 	int		last_type;
 	unsigned	depth;
 	int		total_link_count;
@@ -1758,22 +1758,36 @@ static inline int handle_dots(struct nameidata *nd, int type)
 	if (type == LAST_DOTDOT) {
 		int error = 0;
 
-		/*
-		 * LOOKUP_BENEATH resolving ".." is not currently safe -- races
-		 * can cause our parent to have moved outside of the root and
-		 * us to skip over it.
-		 */
-		if (unlikely(nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT)))
-			return -EXDEV;
 		if (!nd->root.mnt) {
 			error = set_root(nd);
 			if (error)
 				return error;
 		}
-		if (nd->flags & LOOKUP_RCU) {
-			return follow_dotdot_rcu(nd);
-		} else
-			return follow_dotdot(nd);
+		if (nd->flags & LOOKUP_RCU)
+			error = follow_dotdot_rcu(nd);
+		else
+			error = follow_dotdot(nd);
+		if (error)
+			return error;
+
+		if (unlikely(nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT))) {
+			bool m_retry = read_seqretry(&mount_lock, nd->m_seq);
+			bool r_retry = read_seqretry(&rename_lock, nd->r_seq);
+
+			/*
+			 * Don't bother checking unless there's a racing
+			 * rename(2) or MS_MOVE.
+			 */
+			if (likely(!m_retry && !r_retry))
+				return 0;
+
+			if (m_retry && !(nd->flags & LOOKUP_RCU))
+				nd->m_seq = read_seqbegin(&mount_lock);
+			if (r_retry)
+				nd->r_seq = read_seqbegin(&rename_lock);
+			if (!path_is_under(&nd->path, &nd->root))
+				return -EXDEV;
+		}
 	}
 	return 0;
 }
@@ -2245,6 +2259,11 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
 	nd->depth = 0;
+
+	nd->m_seq = read_seqbegin(&mount_lock);
+	if (flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT))
+		nd->r_seq = read_seqbegin(&rename_lock);
+
 	if (flags & LOOKUP_ROOT) {
 		struct dentry *root = nd->root.dentry;
 		struct inode *inode = root->d_inode;
@@ -2266,8 +2285,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	nd->path.mnt = NULL;
 	nd->path.dentry = NULL;
 
-	nd->m_seq = read_seqbegin(&mount_lock);
-
 	/* LOOKUP_IN_ROOT treats absolute paths as being relative-to-dirfd. */
 	if (flags & LOOKUP_IN_ROOT)
 		while (*s == '/')
-- 
2.22.0


^ permalink raw reply related

* [PATCH RESEND v11 1/8] namei: obey trailing magic-link DAC permissions
From: Aleksa Sarai @ 2019-08-20  3:33 UTC (permalink / raw)
  To: Al Viro, Jeff Layton, J. Bruce Fields, Arnd Bergmann,
	David Howells, Shuah Khan, Shuah Khan
  Cc: linux-ia64, linux-sh, Alexei Starovoitov, Oleg Nesterov,
	linux-kselftest, sparclinux, linux-arch, linux-s390,
	Tycho Andersen, Aleksa Sarai, linux-arm-kernel, linux-mips,
	linux-xtensa, Kees Cook, Jann Horn, linuxppc-dev, Aleksa Sarai,
	Andy Lutomirski, David Drysdale, Christian Brauner, linux-parisc,
	linux-m68k, linux-api, Chanho Min, linux-kernel, Eric Biederman,
	linux-alpha, linux-fsdevel, Andrew Morton, Linus Torvalds,
	containers
In-Reply-To: <20190820033406.29796-1-cyphar@cyphar.com>

The ability for userspace to "re-open" file descriptors through
/proc/self/fd has been a very useful tool for all sorts of usecases
(container runtimes are one common example). However, the current
interface for doing this has resulted in some pretty subtle security
holes. Userspace can re-open a file descriptor with more permissions
than the original, which can result in cases such as /proc/$pid/exe
being re-opened O_RDWR at a later date even though (by definition)
/proc/$pid/exe cannot be opened for writing. When combined with O_PATH
the results can get even more confusing.

We cannot block this outright. Aside from userspace already depending on
it, it's a useful feature which can actually increase the security of
userspace. For instance, LXC keeps an O_PATH of the container's
/dev/pts/ptmx that gets re-opened to create new ptys and then uses
TIOCGPTPEER to get the slave end. This allows for pty allocation without
resolving paths inside an (untrusted) container's rootfs. There isn't a
trivial way of doing this that is as straight-forward and safe as O_PATH
re-opening.

Instead we have to restrict it in such a way that it doesn't break
(good) users but does block potential attackers. The solution applied in
this patch is to restrict *re-opening* (not resolution through)
magic-links by requiring that mode of the link be obeyed. Normal
symlinks have modes of a+rwx but magic-links have other modes. These
magic-link modes were historically ignored during path resolution, but
they've now been re-purposed for more useful ends.

It is also necessary to define semantics for the mode of an O_PATH
descriptor, since re-opening a magic-link through an O_PATH needs to be
just as restricted as the corresponding magic-link -- otherwise the
above protection can be bypassed. There are two distinct cases:

 1. The target is a regular file (not a magic-link). Userspace depends
    on being able to re-open the O_PATH of a regular file, so we must
    define the mode to be a+rwx.

 2. The target is a magic-link. In this case, we simply copy the mode of
    the magic-link. This results in an O_PATH of a magic-link
    effectively acting as a no-op in terms of how much re-opening
    privileges a process has.

CAP_DAC_OVERRIDE can be used to override all of these restrictions, but
we only permit &init_userns's capabilities to affect these semantics.
The reason for this is that there isn't a clear way to track what
user_ns is the original owner of a given O_PATH chain -- thus an
unprivileged user could create a new userns and O_PATH the file
descriptor, owning it. All signs would indicate that the user really
does have CAP_DAC_OVERRIDE over the new descriptor and the protection
would be bypassed. We thus opt for the more conservative approach.

I have run this patch on several machines for several days. So far, the
only processes which have hit this case ("loadkeys" and "kbd_mode" from
the kbd package[1]) gracefully handle the permission error and do not
cause any user-visible problems. In order to give users a heads-up, a
warning is output to dmesg whenever may_open_magiclink() refuses access.

[1]: http://git.altlinux.org/people/legion/packages/kbd.git

Suggested-by: Andy Lutomirski <luto@kernel.org>
Suggested-by: Christian Brauner <christian@brauner.io>
Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
---
 Documentation/filesystems/path-lookup.rst |  12 +--
 fs/internal.h                             |   1 +
 fs/namei.c                                | 105 +++++++++++++++++++---
 fs/open.c                                 |   3 +-
 fs/proc/fd.c                              |  23 ++++-
 include/linux/fs.h                        |   4 +
 include/linux/namei.h                     |   1 +
 7 files changed, 130 insertions(+), 19 deletions(-)

diff --git a/Documentation/filesystems/path-lookup.rst b/Documentation/filesystems/path-lookup.rst
index 434a07b0002b..a57d78ec8bee 100644
--- a/Documentation/filesystems/path-lookup.rst
+++ b/Documentation/filesystems/path-lookup.rst
@@ -1310,12 +1310,14 @@ longer needed.
 ``LOOKUP_JUMPED`` means that the current dentry was chosen not because
 it had the right name but for some other reason.  This happens when
 following "``..``", following a symlink to ``/``, crossing a mount point
-or accessing a "``/proc/$PID/fd/$FD``" symlink.  In this case the
-filesystem has not been asked to revalidate the name (with
-``d_revalidate()``).  In such cases the inode may still need to be
-revalidated, so ``d_op->d_weak_revalidate()`` is called if
+or accessing a "``/proc/$PID/fd/$FD``" symlink (also known as a "magic
+link"). In this case the filesystem has not been asked to revalidate the
+name (with ``d_revalidate()``).  In such cases the inode may still need
+to be revalidated, so ``d_op->d_weak_revalidate()`` is called if
 ``LOOKUP_JUMPED`` is set when the look completes - which may be at the
-final component or, when creating, unlinking, or renaming, at the penultimate component.
+final component or, when creating, unlinking, or renaming, at the
+penultimate component. ``LOOKUP_MAGICLINK_JUMPED`` is set alongside
+``LOOKUP_JUMPED`` if a magic-link was traversed.
 
 Final-component flags
 ~~~~~~~~~~~~~~~~~~~~~
diff --git a/fs/internal.h b/fs/internal.h
index 315fcd8d237c..f48449a43626 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -119,6 +119,7 @@ struct open_flags {
 	int acc_mode;
 	int intent;
 	int lookup_flags;
+	fmode_t opath_mask;
 };
 extern struct file *do_filp_open(int dfd, struct filename *pathname,
 		const struct open_flags *op);
diff --git a/fs/namei.c b/fs/namei.c
index 209c51a5226c..54d57dad0f91 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -872,7 +872,7 @@ void nd_jump_link(struct path *path)
 
 	nd->path = *path;
 	nd->inode = nd->path.dentry->d_inode;
-	nd->flags |= LOOKUP_JUMPED;
+	nd->flags |= LOOKUP_JUMPED | LOOKUP_MAGICLINK_JUMPED;
 }
 
 static inline void put_link(struct nameidata *nd)
@@ -1066,6 +1066,7 @@ const char *get_link(struct nameidata *nd)
 		return ERR_PTR(error);
 
 	nd->last_type = LAST_BIND;
+	nd->flags &= ~LOOKUP_MAGICLINK_JUMPED;
 	res = READ_ONCE(inode->i_link);
 	if (!res) {
 		const char * (*get)(struct dentry *, struct inode *,
@@ -3501,16 +3502,73 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	return error;
 }
 
-static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file)
+/**
+ * may_reopen_magiclink - Check permissions for opening a trailing magic-link
+ * @upgrade_mask: the upgrade-mask of the magic-link
+ * @acc_mode: ACC_MODE which the user is attempting
+ *
+ * We block magic-link re-opening if the @upgrade_mask is more strict than the
+ * @acc_mode being requested, unless the user is capable(CAP_DAC_OVERRIDE).
+ *
+ * Returns 0 if successful, -EACCES on error.
+ */
+static int may_open_magiclink(fmode_t upgrade_mask, int acc_mode)
 {
-	struct path path;
-	int error = path_lookupat(nd, flags, &path);
-	if (!error) {
-		audit_inode(nd->name, path.dentry, 0);
-		error = vfs_open(&path, file);
-		path_put(&path);
-	}
-	return error;
+	/*
+	 * We only allow for init_userns to be able to override magic-links.
+	 * This is done to avoid cases where an unprivileged userns could take
+	 * an O_PATH of the fd, resulting in it being very unclear whether
+	 * CAP_DAC_OVERRIDE should work on the new O_PATH fd (given that it
+	 * pipes through to the underlying file).
+	 */
+	if (capable(CAP_DAC_OVERRIDE))
+		return 0;
+
+	if ((acc_mode & MAY_READ) &&
+	    !(upgrade_mask & (FMODE_READ | FMODE_PATH_READ)))
+		goto err;
+	if ((acc_mode & MAY_WRITE) &&
+	    !(upgrade_mask & (FMODE_WRITE | FMODE_PATH_WRITE)))
+		goto err;
+
+	return 0;
+
+err:
+	pr_warn_ratelimited("%s[%d]: magic-link re-open blocked ('%s%s%s' requested with an upgrade-mask of '%s%s%s%s')",
+		current->comm, task_pid_nr(current),
+		(acc_mode & MAY_READ) ? "r" : "",
+		(acc_mode & MAY_WRITE) ? "w" : "",
+		(acc_mode & MAY_EXEC) ? "x" : "",
+		(upgrade_mask & FMODE_READ) ? "r" : "",
+		(upgrade_mask & FMODE_PATH_READ) ? "R" : "",
+		(upgrade_mask & FMODE_WRITE) ? "w" : "",
+		(upgrade_mask & FMODE_PATH_WRITE) ? "W" : "");
+	return -EACCES;
+}
+
+static int trailing_magiclink(struct nameidata *nd, int acc_mode,
+			      fmode_t *opath_mask)
+{
+	struct inode *inode = nd->link_inode;
+	fmode_t upgrade_mask = 0;
+
+	/* Was the trailing_symlink() a magic-link? */
+	if (!(nd->flags & LOOKUP_MAGICLINK_JUMPED))
+		return 0;
+
+	/*
+	 * Figure out the upgrade-mask of the link_inode. Since these aren't
+	 * strictly POSIX semantics we don't do an acl_permission_check() here,
+	 * so we only care that at least one bit is set for each upgrade-mode.
+	 */
+	if (inode->i_mode & S_IRUGO)
+		upgrade_mask |= FMODE_PATH_READ;
+	if (inode->i_mode & S_IWUGO)
+		upgrade_mask |= FMODE_PATH_WRITE;
+	/* Restrict the O_PATH upgrade-mask of the caller. */
+	if (opath_mask)
+		*opath_mask &= upgrade_mask;
+	return may_open_magiclink(upgrade_mask, acc_mode);
 }
 
 static struct file *path_openat(struct nameidata *nd,
@@ -3526,13 +3584,38 @@ static struct file *path_openat(struct nameidata *nd,
 	if (unlikely(file->f_flags & __O_TMPFILE)) {
 		error = do_tmpfile(nd, flags, op, file);
 	} else if (unlikely(file->f_flags & O_PATH)) {
-		error = do_o_path(nd, flags, file);
+		/* Inlined path_lookupat() with a trailing_magiclink() check. */
+		fmode_t opath_mask = op->opath_mask;
+		const char *s = path_init(nd, flags);
+
+		while (!(error = link_path_walk(s, nd))
+			&& ((error = lookup_last(nd)) > 0)) {
+			s = trailing_symlink(nd);
+			error = trailing_magiclink(nd, op->acc_mode, &opath_mask);
+			if (error)
+				s = ERR_PTR(error);
+		}
+		if (!error)
+			error = complete_walk(nd);
+
+		if (!error && nd->flags & LOOKUP_DIRECTORY)
+			if (!d_can_lookup(nd->path.dentry))
+				error = -ENOTDIR;
+		if (!error) {
+			audit_inode(nd->name, nd->path.dentry, 0);
+			error = vfs_open(&nd->path, file);
+			file->f_mode |= opath_mask;
+		}
+		terminate_walk(nd);
 	} else {
 		const char *s = path_init(nd, flags);
 		while (!(error = link_path_walk(s, nd)) &&
 			(error = do_last(nd, file, op)) > 0) {
 			nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
 			s = trailing_symlink(nd);
+			error = trailing_magiclink(nd, op->acc_mode, NULL);
+			if (error)
+				s = ERR_PTR(error);
 		}
 		terminate_walk(nd);
 	}
diff --git a/fs/open.c b/fs/open.c
index a59abe3c669a..806a75d685e1 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1001,8 +1001,9 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 		acc_mode |= MAY_APPEND;
 
 	op->acc_mode = acc_mode;
-
 	op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
+	/* For O_PATH backwards-compatibility we default to an all-set mask. */
+	op->opath_mask = FMODE_PATH_READ | FMODE_PATH_WRITE;
 
 	if (flags & O_CREAT) {
 		op->intent |= LOOKUP_CREATE;
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 81882a13212d..9b7d8becb002 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -104,11 +104,30 @@ static void tid_fd_update_inode(struct task_struct *task, struct inode *inode,
 	task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
 
 	if (S_ISLNK(inode->i_mode)) {
+		/*
+		 * Always set +x (depending on the fmode type), since there
+		 * currently aren't FMODE_PATH_EXEC restrictions and there is
+		 * no O_MAYEXEC yet. This might change in the future, in which
+		 * case we will restrict +x.
+		 */
 		unsigned i_mode = S_IFLNK;
+		if (f_mode & FMODE_PATH)
+			i_mode |= S_IXGRP;
+		else
+			i_mode |= S_IXUSR;
+		/*
+		 * Construct the mode bits based on the open-mode. The u+rwx
+		 * bits are for "ordinary" open modes while g+rwx are for
+		 * O_PATH modes.
+		 */
 		if (f_mode & FMODE_READ)
-			i_mode |= S_IRUSR | S_IXUSR;
+			i_mode |= S_IRUSR;
 		if (f_mode & FMODE_WRITE)
-			i_mode |= S_IWUSR | S_IXUSR;
+			i_mode |= S_IWUSR;
+		if (f_mode & FMODE_PATH_READ)
+			i_mode |= S_IRGRP;
+		if (f_mode & FMODE_PATH_WRITE)
+			i_mode |= S_IWGRP;
 		inode->i_mode = i_mode;
 	}
 	security_task_to_inode(task, inode);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 997a530ff4e9..a9ad596b28e2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -173,6 +173,10 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* File does not contribute to nr_files count */
 #define FMODE_NOACCOUNT		((__force fmode_t)0x20000000)
 
+/* File is an O_PATH descriptor which can be upgraded to (read, write). */
+#define FMODE_PATH_READ		((__force fmode_t)0x40000000)
+#define FMODE_PATH_WRITE	((__force fmode_t)0x80000000)
+
 /*
  * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
  * that indicates that they should check the contents of the iovec are
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 9138b4471dbf..bd6d3eb7764d 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -49,6 +49,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_ROOT		0x2000
 #define LOOKUP_EMPTY		0x4000
 #define LOOKUP_DOWN		0x8000
+#define LOOKUP_MAGICLINK_JUMPED	0x10000
 
 extern int path_pts(struct path *path);
 
-- 
2.22.0


^ permalink raw reply related

* [PATCH RESEND v11 2/8] procfs: switch magic-link modes to be more sane
From: Aleksa Sarai @ 2019-08-20  3:34 UTC (permalink / raw)
  To: Al Viro, Jeff Layton, J. Bruce Fields, Arnd Bergmann,
	David Howells, Shuah Khan, Shuah Khan
  Cc: linux-ia64, linux-sh, Alexei Starovoitov, Oleg Nesterov,
	linux-kselftest, sparclinux, linux-arch, linux-s390,
	Tycho Andersen, Aleksa Sarai, linux-arm-kernel, linux-mips,
	linux-xtensa, Kees Cook, Jann Horn, linuxppc-dev, Aleksa Sarai,
	Andy Lutomirski, David Drysdale, Christian Brauner, linux-parisc,
	linux-m68k, linux-api, Chanho Min, linux-kernel, Eric Biederman,
	linux-alpha, linux-fsdevel, Andrew Morton, Linus Torvalds,
	containers
In-Reply-To: <20190820033406.29796-1-cyphar@cyphar.com>

Now that magic-link modes are obeyed for file re-opening purposes, some
of the pre-existing magic-link modes need to be adjusted to be more
semantically correct.

The most blatant example of this is /proc/self/exe, which had a mode of
a+rwx even though tautologically the file could never be opened for
writing (because it is the current->mm of a live process).

With the new O_PATH restrictions, changing the default mode of these
magic-links allows us to avoid delayed-access attacks such as we saw in
CVE-2019-5736.

Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
---
 fs/proc/base.c       | 20 ++++++++++----------
 fs/proc/namespaces.c |  2 +-
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/fs/proc/base.c b/fs/proc/base.c
index ebea9501afb8..297242174402 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -133,9 +133,9 @@ struct pid_entry {
 
 #define DIR(NAME, MODE, iops, fops)	\
 	NOD(NAME, (S_IFDIR|(MODE)), &iops, &fops, {} )
-#define LNK(NAME, get_link)					\
-	NOD(NAME, (S_IFLNK|S_IRWXUGO),				\
-		&proc_pid_link_inode_operations, NULL,		\
+#define LNK(NAME, MODE, get_link)			\
+	NOD(NAME, (S_IFLNK|(MODE)),			\
+		&proc_pid_link_inode_operations, NULL,	\
 		{ .proc_get_link = get_link } )
 #define REG(NAME, MODE, fops)				\
 	NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {})
@@ -3028,9 +3028,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("numa_maps",  S_IRUGO, proc_pid_numa_maps_operations),
 #endif
 	REG("mem",        S_IRUSR|S_IWUSR, proc_mem_operations),
-	LNK("cwd",        proc_cwd_link),
-	LNK("root",       proc_root_link),
-	LNK("exe",        proc_exe_link),
+	LNK("cwd",        S_IRWXUGO, proc_cwd_link),
+	LNK("root",       S_IRWXUGO, proc_root_link),
+	LNK("exe",        S_IRUGO|S_IXUGO, proc_exe_link),
 	REG("mounts",     S_IRUGO, proc_mounts_operations),
 	REG("mountinfo",  S_IRUGO, proc_mountinfo_operations),
 	REG("mountstats", S_IRUSR, proc_mountstats_operations),
@@ -3429,11 +3429,11 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations),
 #endif
 	REG("mem",       S_IRUSR|S_IWUSR, proc_mem_operations),
-	LNK("cwd",       proc_cwd_link),
-	LNK("root",      proc_root_link),
-	LNK("exe",       proc_exe_link),
+	LNK("cwd",       S_IRWXUGO, proc_cwd_link),
+	LNK("root",      S_IRWXUGO, proc_root_link),
+	LNK("exe",       S_IRUGO|S_IXUGO, proc_exe_link),
 	REG("mounts",    S_IRUGO, proc_mounts_operations),
-	REG("mountinfo",  S_IRUGO, proc_mountinfo_operations),
+	REG("mountinfo", S_IRUGO, proc_mountinfo_operations),
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
 	REG("smaps",     S_IRUGO, proc_pid_smaps_operations),
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index dd2b35f78b09..cd1e130913f7 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -94,7 +94,7 @@ static struct dentry *proc_ns_instantiate(struct dentry *dentry,
 	struct inode *inode;
 	struct proc_inode *ei;
 
-	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRWXUGO);
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRUGO);
 	if (!inode)
 		return ERR_PTR(-ENOENT);
 
-- 
2.22.0


^ permalink raw reply related

* Re: [PATCH 2/3] of_pmem: Add memory ranges which took a mce to bad range
From: Oliver O'Halloran @ 2019-08-20  8:41 UTC (permalink / raw)
  To: Santosh Sivaraj
  Cc: linux-nvdimm, Aneesh Kumar K.V, Mahesh Salgaonkar,
	Chandan Rajendra, Dan Williams, linuxppc-dev
In-Reply-To: <20190820023030.18232-3-santosh@fossix.org>

On Tue, Aug 20, 2019 at 12:30 PM Santosh Sivaraj <santosh@fossix.org> wrote:
>
> Subscribe to the MCE notification and add the physical address which
> generated a memory error to nvdimm bad range.

Uh... I should have looked a bit closer at this on v1.

a) of_pmem.c isn't part of the powerpc tree. You should have CCed this
to the nvdimm list since you'll need an Ack from Dan Williams.
b) of_pmem isn't powerpc specific. Adding a pile of powerpc specific
machine check parsing means it's not going to compile on other DT
platforms.
c) all this appears to be copied and pasted from the papr_scm version of this.

Considering this is pretty similar in spirit to what's done on x86
today (drivers/acpi/nfit/mce.c) I think you would get more milage out
of moving the address matching into libnvdimm itself. Machine check
handling is always going to be arch specific, but memory errors could
be re-emitted by the arch code into a more generic notifier chain that
libnvdimm use. There's probably other uses in mm/ for such a chain
too.

Oliver


> Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
> ---
>  drivers/nvdimm/of_pmem.c | 151 +++++++++++++++++++++++++++++++++------
>  1 file changed, 131 insertions(+), 20 deletions(-)
>
> diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c
> index a0c8dcfa0bf9..155e56862fdf 100644
> --- a/drivers/nvdimm/of_pmem.c
> +++ b/drivers/nvdimm/of_pmem.c
> @@ -8,6 +8,9 @@
>  #include <linux/module.h>
>  #include <linux/ioport.h>
>  #include <linux/slab.h>
> +#include <linux/string.h>
> +#include <linux/nd.h>
> +#include <asm/mce.h>
>
>  static const struct attribute_group *region_attr_groups[] = {
>         &nd_region_attribute_group,
> @@ -25,11 +28,77 @@ struct of_pmem_private {
>         struct nvdimm_bus *bus;
>  };
>
> +struct of_pmem_region {
> +       struct of_pmem_private *priv;
> +       struct nd_region_desc *region_desc;
> +       struct nd_region *region;
> +       struct list_head region_list;
> +};
> +
> +LIST_HEAD(pmem_regions);
> +DEFINE_MUTEX(pmem_region_lock);
> +
> +static int handle_mce_ue(struct notifier_block *nb, unsigned long val,
> +                        void *data)
> +{
> +       struct machine_check_event *evt = data;
> +       struct of_pmem_region *pmem_region;
> +       u64 aligned_addr, phys_addr;
> +       bool found = false;
> +
> +       if (evt->error_type != MCE_ERROR_TYPE_UE)
> +               return NOTIFY_DONE;
> +
> +       if (list_empty(&pmem_regions))
> +               return NOTIFY_DONE;
> +
> +       phys_addr = evt->u.ue_error.physical_address +
> +               (evt->u.ue_error.effective_address & ~PAGE_MASK);
> +
> +       if (!evt->u.ue_error.physical_address_provided ||
> +           !is_zone_device_page(pfn_to_page(phys_addr >> PAGE_SHIFT)))
> +               return NOTIFY_DONE;
> +
> +       mutex_lock(&pmem_region_lock);
> +       list_for_each_entry(pmem_region, &pmem_regions, region_list) {
> +               struct resource *res = pmem_region->region_desc->res;
> +
> +               if (phys_addr >= res->start && phys_addr <= res->end) {
> +                       found = true;
> +                       break;
> +               }
> +       }
> +       mutex_unlock(&pmem_region_lock);
> +
> +       if (!found)
> +               return NOTIFY_DONE;
> +
> +       aligned_addr = ALIGN_DOWN(phys_addr, L1_CACHE_BYTES);
> +
> +       if (nvdimm_bus_add_badrange(pmem_region->priv->bus, aligned_addr,
> +                                   L1_CACHE_BYTES))
> +               return NOTIFY_DONE;
> +
> +       pr_debug("Add memory range (0x%llx -- 0x%llx) as bad range\n",
> +                aligned_addr, aligned_addr + L1_CACHE_BYTES);
> +
> +
> +       nvdimm_region_notify(pmem_region->region, NVDIMM_REVALIDATE_POISON);
> +
> +       return NOTIFY_OK;
> +}
> +
> +static struct notifier_block mce_ue_nb = {
> +       .notifier_call = handle_mce_ue
> +};
> +
>  static int of_pmem_region_probe(struct platform_device *pdev)
>  {
>         struct of_pmem_private *priv;
>         struct device_node *np;
>         struct nvdimm_bus *bus;
> +       struct of_pmem_region *pmem_region;
> +       struct nd_region_desc *ndr_desc;
>         bool is_volatile;
>         int i;
>
> @@ -58,32 +127,49 @@ static int of_pmem_region_probe(struct platform_device *pdev)
>                         is_volatile ? "volatile" : "non-volatile",  np);
>
>         for (i = 0; i < pdev->num_resources; i++) {
> -               struct nd_region_desc ndr_desc;
>                 struct nd_region *region;
>
> -               /*
> -                * NB: libnvdimm copies the data from ndr_desc into it's own
> -                * structures so passing a stack pointer is fine.
> -                */
> -               memset(&ndr_desc, 0, sizeof(ndr_desc));
> -               ndr_desc.attr_groups = region_attr_groups;
> -               ndr_desc.numa_node = dev_to_node(&pdev->dev);
> -               ndr_desc.target_node = ndr_desc.numa_node;
> -               ndr_desc.res = &pdev->resource[i];
> -               ndr_desc.of_node = np;
> -               set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
> +               ndr_desc = kzalloc(sizeof(struct nd_region_desc), GFP_KERNEL);
> +               if (!ndr_desc) {
> +                       nvdimm_bus_unregister(priv->bus);
> +                       kfree(priv);
> +                       return -ENOMEM;
> +               }
> +
> +               ndr_desc->attr_groups = region_attr_groups;
> +               ndr_desc->numa_node = dev_to_node(&pdev->dev);
> +               ndr_desc->target_node = ndr_desc->numa_node;
> +               ndr_desc->res = &pdev->resource[i];
> +               ndr_desc->of_node = np;
> +               set_bit(ND_REGION_PAGEMAP, &ndr_desc->flags);
>
>                 if (is_volatile)
> -                       region = nvdimm_volatile_region_create(bus, &ndr_desc);
> +                       region = nvdimm_volatile_region_create(bus, ndr_desc);
>                 else
> -                       region = nvdimm_pmem_region_create(bus, &ndr_desc);
> +                       region = nvdimm_pmem_region_create(bus, ndr_desc);
>
> -               if (!region)
> +               if (!region) {
>                         dev_warn(&pdev->dev, "Unable to register region %pR from %pOF\n",
> -                                       ndr_desc.res, np);
> -               else
> -                       dev_dbg(&pdev->dev, "Registered region %pR from %pOF\n",
> -                                       ndr_desc.res, np);
> +                                       ndr_desc->res, np);
> +                       continue;
> +               }
> +
> +               dev_dbg(&pdev->dev, "Registered region %pR from %pOF\n",
> +                       ndr_desc->res, np);
> +
> +               pmem_region = kzalloc(sizeof(struct of_pmem_region),
> +                                     GFP_KERNEL);
> +               if (!pmem_region)
> +                       continue;
> +
> +               pmem_region->region_desc = ndr_desc;
> +               pmem_region->region = region;
> +               pmem_region->priv = priv;
> +
> +               /* Save regions registered for use by the notification code */
> +               mutex_lock(&pmem_region_lock);
> +               list_add_tail(&pmem_region->region_list, &pmem_regions);
> +               mutex_unlock(&pmem_region_lock);
>         }
>
>         return 0;
> @@ -92,6 +178,13 @@ static int of_pmem_region_probe(struct platform_device *pdev)
>  static int of_pmem_region_remove(struct platform_device *pdev)
>  {
>         struct of_pmem_private *priv = platform_get_drvdata(pdev);
> +       struct of_pmem_region *r, *t;
> +
> +       list_for_each_entry_safe(r, t, &pmem_regions, region_list) {
> +               list_del(&(r->region_list));
> +               kfree(r->region_desc);
> +               kfree(r);
> +       }
>
>         nvdimm_bus_unregister(priv->bus);
>         kfree(priv);
> @@ -113,7 +206,25 @@ static struct platform_driver of_pmem_region_driver = {
>         },
>  };
>
> -module_platform_driver(of_pmem_region_driver);
> +static int __init of_pmem_init(void)
> +{
> +       int ret;
> +
> +       ret = platform_driver_register(&of_pmem_region_driver);
> +       if (!ret)
> +               mce_register_notifier(&mce_ue_nb);
> +
> +       return ret;
> +}
> +module_init(of_pmem_init);
> +
> +static void __exit of_pmem_exit(void)
> +{
> +       mce_unregister_notifier(&mce_ue_nb);
> +       platform_driver_unregister(&of_pmem_region_driver);
> +}
> +module_exit(of_pmem_exit);
> +
>  MODULE_DEVICE_TABLE(of, of_pmem_region_match);
>  MODULE_LICENSE("GPL");
>  MODULE_AUTHOR("IBM Corporation");
> --
> 2.21.0
>

^ permalink raw reply

* [PATCH v11 7/7] powerpc: add machine check safe copy_to_user
From: Santosh Sivaraj @ 2019-08-20  8:13 UTC (permalink / raw)
  To: linuxppc-dev, Linux Kernel
  Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
	Chandan Rajendra, Reza Arbab
In-Reply-To: <20190820081352.8641-1-santosh@fossix.org>

Use  memcpy_mcsafe() implementation to define copy_to_user_mcsafe()

Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
---
 arch/powerpc/Kconfig               |  1 +
 arch/powerpc/include/asm/uaccess.h | 14 ++++++++++++++
 2 files changed, 15 insertions(+)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d8dcd8820369..39c738aa600a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -136,6 +136,7 @@ config PPC
 	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION)
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if PPC64
+	select ARCH_HAS_UACCESS_MCSAFE		if PPC64
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_KEEP_MEMBLOCK
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 8b03eb44e876..15002b51ff18 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -387,6 +387,20 @@ static inline unsigned long raw_copy_to_user(void __user *to,
 	return ret;
 }
 
+static __always_inline unsigned long __must_check
+copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n)
+{
+	if (likely(check_copy_size(from, n, true))) {
+		if (access_ok(to, n)) {
+			allow_write_to_user(to, n);
+			n = memcpy_mcsafe((void *)to, from, n);
+			prevent_write_to_user(to, n);
+		}
+	}
+
+	return n;
+}
+
 extern unsigned long __clear_user(void __user *addr, unsigned long size);
 
 static inline unsigned long clear_user(void __user *addr, unsigned long size)
-- 
2.21.0


^ permalink raw reply related

* [PATCH v11 6/7] powerpc/memcpy: Add memcpy_mcsafe for pmem
From: Santosh Sivaraj @ 2019-08-20  8:13 UTC (permalink / raw)
  To: linuxppc-dev, Linux Kernel
  Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
	Chandan Rajendra, Reza Arbab
In-Reply-To: <20190820081352.8641-1-santosh@fossix.org>

From: Balbir Singh <bsingharora@gmail.com>

The pmem infrastructure uses memcpy_mcsafe in the pmem layer so as to
convert machine check exceptions into a return value on failure in case
a machine check exception is encountered during the memcpy. The return
value is the number of bytes remaining to be copied.

This patch largely borrows from the copyuser_power7 logic and does not add
the VMX optimizations, largely to keep the patch simple. If needed those
optimizations can be folded in.

Signed-off-by: Balbir Singh <bsingharora@gmail.com>
[arbab@linux.ibm.com: Added symbol export]
Co-developed-by: Santosh Sivaraj <santosh@fossix.org>
Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
---
 arch/powerpc/include/asm/string.h   |   2 +
 arch/powerpc/lib/Makefile           |   2 +-
 arch/powerpc/lib/memcpy_mcsafe_64.S | 242 ++++++++++++++++++++++++++++
 3 files changed, 245 insertions(+), 1 deletion(-)
 create mode 100644 arch/powerpc/lib/memcpy_mcsafe_64.S

diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index 9bf6dffb4090..b72692702f35 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -53,7 +53,9 @@ void *__memmove(void *to, const void *from, __kernel_size_t n);
 #ifndef CONFIG_KASAN
 #define __HAVE_ARCH_MEMSET32
 #define __HAVE_ARCH_MEMSET64
+#define __HAVE_ARCH_MEMCPY_MCSAFE
 
+extern int memcpy_mcsafe(void *dst, const void *src, __kernel_size_t sz);
 extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t);
 extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t);
 extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t);
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index eebc782d89a5..fa6b1b657b43 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -39,7 +39,7 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
 			       memcpy_power7.o
 
 obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
-	   memcpy_64.o pmem.o
+	   memcpy_64.o pmem.o memcpy_mcsafe_64.o
 
 obj64-$(CONFIG_SMP)	+= locks.o
 obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o
diff --git a/arch/powerpc/lib/memcpy_mcsafe_64.S b/arch/powerpc/lib/memcpy_mcsafe_64.S
new file mode 100644
index 000000000000..949976dc115d
--- /dev/null
+++ b/arch/powerpc/lib/memcpy_mcsafe_64.S
@@ -0,0 +1,242 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) IBM Corporation, 2011
+ * Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
+ * Author - Balbir Singh <bsingharora@gmail.com>
+ */
+#include <asm/ppc_asm.h>
+#include <asm/errno.h>
+#include <asm/export.h>
+
+	.macro err1
+100:
+	EX_TABLE(100b,.Ldo_err1)
+	.endm
+
+	.macro err2
+200:
+	EX_TABLE(200b,.Ldo_err2)
+	.endm
+
+	.macro err3
+300:	EX_TABLE(300b,.Ldone)
+	.endm
+
+.Ldo_err2:
+	ld	r22,STK_REG(R22)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+.Ldo_err1:
+	/* Do a byte by byte copy to get the exact remaining size */
+	mtctr	r7
+46:
+err3;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err3;	stb	r0,0(r3)
+	addi	r3,r3,1
+	bdnz	46b
+	li	r3,0
+	blr
+
+.Ldone:
+	mfctr	r3
+	blr
+
+
+_GLOBAL(memcpy_mcsafe)
+	mr	r7,r5
+	cmpldi	r5,16
+	blt	.Lshort_copy
+
+.Lcopy:
+	/* Get the source 8B aligned */
+	neg	r6,r4
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-3)
+
+	bf	cr7*4+3,1f
+err1;	lbz	r0,0(r4)
+	addi	r4,r4,1
+err1;	stb	r0,0(r3)
+	addi	r3,r3,1
+	subi	r7,r7,1
+
+1:	bf	cr7*4+2,2f
+err1;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+	subi	r7,r7,2
+
+2:	bf	cr7*4+1,3f
+err1;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+	subi	r7,r7,4
+
+3:	sub	r5,r5,r6
+	cmpldi	r5,128
+	blt	5f
+
+	mflr	r0
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+	std	r17,STK_REG(R17)(r1)
+	std	r18,STK_REG(R18)(r1)
+	std	r19,STK_REG(R19)(r1)
+	std	r20,STK_REG(R20)(r1)
+	std	r21,STK_REG(R21)(r1)
+	std	r22,STK_REG(R22)(r1)
+	std	r0,STACKFRAMESIZE+16(r1)
+
+	srdi	r6,r5,7
+	mtctr	r6
+
+	/* Now do cacheline (128B) sized loads and stores. */
+	.align	5
+4:
+err2;	ld	r0,0(r4)
+err2;	ld	r6,8(r4)
+err2;	ld	r8,16(r4)
+err2;	ld	r9,24(r4)
+err2;	ld	r10,32(r4)
+err2;	ld	r11,40(r4)
+err2;	ld	r12,48(r4)
+err2;	ld	r14,56(r4)
+err2;	ld	r15,64(r4)
+err2;	ld	r16,72(r4)
+err2;	ld	r17,80(r4)
+err2;	ld	r18,88(r4)
+err2;	ld	r19,96(r4)
+err2;	ld	r20,104(r4)
+err2;	ld	r21,112(r4)
+err2;	ld	r22,120(r4)
+	addi	r4,r4,128
+err2;	std	r0,0(r3)
+err2;	std	r6,8(r3)
+err2;	std	r8,16(r3)
+err2;	std	r9,24(r3)
+err2;	std	r10,32(r3)
+err2;	std	r11,40(r3)
+err2;	std	r12,48(r3)
+err2;	std	r14,56(r3)
+err2;	std	r15,64(r3)
+err2;	std	r16,72(r3)
+err2;	std	r17,80(r3)
+err2;	std	r18,88(r3)
+err2;	std	r19,96(r3)
+err2;	std	r20,104(r3)
+err2;	std	r21,112(r3)
+err2;	std	r22,120(r3)
+	addi	r3,r3,128
+	subi	r7,r7,128
+	bdnz	4b
+
+	clrldi	r5,r5,(64-7)
+
+	/* Up to 127B to go */
+5:	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+6:	bf	cr7*4+1,7f
+err2;	ld	r0,0(r4)
+err2;	ld	r6,8(r4)
+err2;	ld	r8,16(r4)
+err2;	ld	r9,24(r4)
+err2;	ld	r10,32(r4)
+err2;	ld	r11,40(r4)
+err2;	ld	r12,48(r4)
+err2;	ld	r14,56(r4)
+	addi	r4,r4,64
+err2;	std	r0,0(r3)
+err2;	std	r6,8(r3)
+err2;	std	r8,16(r3)
+err2;	std	r9,24(r3)
+err2;	std	r10,32(r3)
+err2;	std	r11,40(r3)
+err2;	std	r12,48(r3)
+err2;	std	r14,56(r3)
+	addi	r3,r3,64
+	subi	r7,r7,64
+
+7:	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r22,STK_REG(R22)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	/* Up to 63B to go */
+	bf	cr7*4+2,8f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+err1;	ld	r8,16(r4)
+err1;	ld	r9,24(r4)
+	addi	r4,r4,32
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+err1;	std	r8,16(r3)
+err1;	std	r9,24(r3)
+	addi	r3,r3,32
+	subi	r7,r7,32
+
+	/* Up to 31B to go */
+8:	bf	cr7*4+3,9f
+err1;	ld	r0,0(r4)
+err1;	ld	r6,8(r4)
+	addi	r4,r4,16
+err1;	std	r0,0(r3)
+err1;	std	r6,8(r3)
+	addi	r3,r3,16
+	subi	r7,r7,16
+
+9:	clrldi	r5,r5,(64-4)
+
+	/* Up to 15B to go */
+.Lshort_copy:
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+err1;	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+err1;	lwz	r6,4(r4)
+	addi	r4,r4,8
+err1;	stw	r0,0(r3)
+err1;	stw	r6,4(r3)
+	addi	r3,r3,8
+	subi	r7,r7,8
+
+12:	bf	cr7*4+1,13f
+err1;	lwz	r0,0(r4)
+	addi	r4,r4,4
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+	subi	r7,r7,4
+
+13:	bf	cr7*4+2,14f
+err1;	lhz	r0,0(r4)
+	addi	r4,r4,2
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+	subi	r7,r7,2
+
+14:	bf	cr7*4+3,15f
+err1;	lbz	r0,0(r4)
+err1;	stb	r0,0(r3)
+
+15:	li	r3,0
+	blr
+
+EXPORT_SYMBOL_GPL(memcpy_mcsafe);
-- 
2.21.0


^ permalink raw reply related

* [PATCH v11 5/7] powerpc/mce: Handle UE event for memcpy_mcsafe
From: Santosh Sivaraj @ 2019-08-20  8:13 UTC (permalink / raw)
  To: linuxppc-dev, Linux Kernel
  Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
	Mahesh Salgaonkar, Chandan Rajendra, Reza Arbab
In-Reply-To: <20190820081352.8641-1-santosh@fossix.org>

From: Balbir Singh <bsingharora@gmail.com>

If we take a UE on one of the instructions with a fixup entry, set nip
to continue execution at the fixup entry. Stop processing the event
further or print it.

Co-developed-by: Reza Arbab <arbab@linux.ibm.com>
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
---
 arch/powerpc/include/asm/mce.h  |  4 +++-
 arch/powerpc/kernel/mce.c       | 16 ++++++++++++++++
 arch/powerpc/kernel/mce_power.c | 15 +++++++++++++--
 3 files changed, 32 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index a4c6a74ad2fb..19a33707d5ef 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -122,7 +122,8 @@ struct machine_check_event {
 			enum MCE_UeErrorType ue_error_type:8;
 			u8		effective_address_provided;
 			u8		physical_address_provided;
-			u8		reserved_1[5];
+			u8		ignore_event;
+			u8		reserved_1[4];
 			u64		effective_address;
 			u64		physical_address;
 			u8		reserved_2[8];
@@ -193,6 +194,7 @@ struct mce_error_info {
 	enum MCE_Initiator	initiator:8;
 	enum MCE_ErrorClass	error_class:8;
 	bool			sync_error;
+	bool			ignore_event;
 };
 
 #define MAX_MC_EVT	100
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index a3b122a685a5..ec4b3e1087be 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -149,6 +149,7 @@ void save_mce_event(struct pt_regs *regs, long handled,
 		if (phys_addr != ULONG_MAX) {
 			mce->u.ue_error.physical_address_provided = true;
 			mce->u.ue_error.physical_address = phys_addr;
+			mce->u.ue_error.ignore_event = mce_err->ignore_event;
 			machine_check_ue_event(mce);
 		}
 	}
@@ -266,8 +267,17 @@ static void machine_process_ue_event(struct work_struct *work)
 		/*
 		 * This should probably queued elsewhere, but
 		 * oh! well
+		 *
+		 * Don't report this machine check because the caller has a
+		 * asked us to ignore the event, it has a fixup handler which
+		 * will do the appropriate error handling and reporting.
 		 */
 		if (evt->error_type == MCE_ERROR_TYPE_UE) {
+			if (evt->u.ue_error.ignore_event) {
+				__this_cpu_dec(mce_ue_count);
+				continue;
+			}
+
 			if (evt->u.ue_error.physical_address_provided) {
 				unsigned long pfn;
 
@@ -301,6 +311,12 @@ static void machine_check_process_queued_event(struct irq_work *work)
 	while (__this_cpu_read(mce_queue_count) > 0) {
 		index = __this_cpu_read(mce_queue_count) - 1;
 		evt = this_cpu_ptr(&mce_event_queue[index]);
+
+		if (evt->error_type == MCE_ERROR_TYPE_UE &&
+		    evt->u.ue_error.ignore_event) {
+			__this_cpu_dec(mce_queue_count);
+			continue;
+		}
 		machine_check_print_event_info(evt, false, false);
 		__this_cpu_dec(mce_queue_count);
 	}
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 714a98e0927f..b6cbe3449358 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -11,6 +11,7 @@
 
 #include <linux/types.h>
 #include <linux/ptrace.h>
+#include <linux/extable.h>
 #include <asm/mmu.h>
 #include <asm/mce.h>
 #include <asm/machdep.h>
@@ -18,6 +19,7 @@
 #include <asm/pte-walk.h>
 #include <asm/sstep.h>
 #include <asm/exception-64s.h>
+#include <asm/extable.h>
 
 /*
  * Convert an address related to an mm to a PFN. NOTE: we are in real
@@ -565,9 +567,18 @@ static int mce_handle_derror(struct pt_regs *regs,
 	return 0;
 }
 
-static long mce_handle_ue_error(struct pt_regs *regs)
+static long mce_handle_ue_error(struct pt_regs *regs,
+				struct mce_error_info *mce_err)
 {
 	long handled = 0;
+	const struct exception_table_entry *entry;
+
+	entry = search_kernel_exception_table(regs->nip);
+	if (entry) {
+		mce_err->ignore_event = true;
+		regs->nip = extable_fixup(entry);
+		return 1;
+	}
 
 	/*
 	 * On specific SCOM read via MMIO we may get a machine check
@@ -600,7 +611,7 @@ static long mce_handle_error(struct pt_regs *regs,
 				&phys_addr);
 
 	if (!handled && mce_err.error_type == MCE_ERROR_TYPE_UE)
-		handled = mce_handle_ue_error(regs);
+		handled = mce_handle_ue_error(regs, &mce_err);
 
 	save_mce_event(regs, handled, &mce_err, regs->nip, addr, phys_addr);
 
-- 
2.21.0


^ permalink raw reply related

* [PATCH v11 4/7] extable: Add function to search only kernel exception table
From: Santosh Sivaraj @ 2019-08-20  8:13 UTC (permalink / raw)
  To: linuxppc-dev, Linux Kernel
  Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
	Chandan Rajendra, Thomas Gleixner, Reza Arbab, Ingo Molnar
In-Reply-To: <20190820081352.8641-1-santosh@fossix.org>

Certain architecture specific operating modes (e.g., in powerpc machine
check handler that is unable to access vmalloc memory), the
search_exception_tables cannot be called because it also searches the
module exception tables if entry is not found in the kernel exception
table.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
---
 include/linux/extable.h |  2 ++
 kernel/extable.c        | 11 +++++++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/linux/extable.h b/include/linux/extable.h
index 41c5b3a25f67..81ecfaa83ad3 100644
--- a/include/linux/extable.h
+++ b/include/linux/extable.h
@@ -19,6 +19,8 @@ void trim_init_extable(struct module *m);
 
 /* Given an address, look for it in the exception tables */
 const struct exception_table_entry *search_exception_tables(unsigned long add);
+const struct exception_table_entry *
+search_kernel_exception_table(unsigned long addr);
 
 #ifdef CONFIG_MODULES
 /* For extable.c to search modules' exception tables. */
diff --git a/kernel/extable.c b/kernel/extable.c
index e23cce6e6092..f6c9406eec7d 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -40,13 +40,20 @@ void __init sort_main_extable(void)
 	}
 }
 
+/* Given an address, look for it in the kernel exception table */
+const
+struct exception_table_entry *search_kernel_exception_table(unsigned long addr)
+{
+	return search_extable(__start___ex_table,
+			      __stop___ex_table - __start___ex_table, addr);
+}
+
 /* Given an address, look for it in the exception tables. */
 const struct exception_table_entry *search_exception_tables(unsigned long addr)
 {
 	const struct exception_table_entry *e;
 
-	e = search_extable(__start___ex_table,
-			   __stop___ex_table - __start___ex_table, addr);
+	e = search_kernel_exception_table(addr);
 	if (!e)
 		e = search_module_extables(addr);
 	return e;
-- 
2.21.0


^ permalink raw reply related

* [PATCH v11 3/7] powerpc/mce: Make machine_check_ue_event() static
From: Santosh Sivaraj @ 2019-08-20  8:13 UTC (permalink / raw)
  To: linuxppc-dev, Linux Kernel
  Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
	Chandan Rajendra, Reza Arbab
In-Reply-To: <20190820081352.8641-1-santosh@fossix.org>

From: Reza Arbab <arbab@linux.ibm.com>

The function doesn't get used outside this file, so make it static.

Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/mce.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index cff31d4a501f..a3b122a685a5 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -34,7 +34,7 @@ static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT],
 
 static void machine_check_process_queued_event(struct irq_work *work);
 static void machine_check_ue_irq_work(struct irq_work *work);
-void machine_check_ue_event(struct machine_check_event *evt);
+static void machine_check_ue_event(struct machine_check_event *evt);
 static void machine_process_ue_event(struct work_struct *work);
 
 static struct irq_work mce_event_process_work = {
@@ -212,7 +212,7 @@ static void machine_check_ue_irq_work(struct irq_work *work)
 /*
  * Queue up the MCE event which then can be handled later.
  */
-void machine_check_ue_event(struct machine_check_event *evt)
+static void machine_check_ue_event(struct machine_check_event *evt)
 {
 	int index;
 
-- 
2.21.0


^ permalink raw reply related

* [PATCH v11 2/7] powerpc/mce: Fix MCE handling for huge pages
From: Santosh Sivaraj @ 2019-08-20  8:13 UTC (permalink / raw)
  To: linuxppc-dev, Linux Kernel
  Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
	Mahesh Salgaonkar, Chandan Rajendra, stable, Reza Arbab
In-Reply-To: <20190820081352.8641-1-santosh@fossix.org>

From: Balbir Singh <bsingharora@gmail.com>

The current code would fail on huge pages addresses, since the shift would
be incorrect. Use the correct page shift value returned by
__find_linux_pte() to get the correct physical address. The code is more
generic and can handle both regular and compound pages.

Fixes: ba41e1e1ccb9 ("powerpc/mce: Hookup derror (load/store) UE errors")
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
[arbab@linux.ibm.com: Fixup pseries_do_memory_failure()]
Signed-off-by: Reza Arbab <arbab@linux.ibm.com>
Tested-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
Cc: stable@vger.kernel.org # v4.15+
---
 arch/powerpc/kernel/mce_power.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index a814d2dfb5b0..714a98e0927f 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -26,6 +26,7 @@
 unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
 {
 	pte_t *ptep;
+	unsigned int shift;
 	unsigned long flags;
 	struct mm_struct *mm;
 
@@ -35,13 +36,18 @@ unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr)
 		mm = &init_mm;
 
 	local_irq_save(flags);
-	if (mm == current->mm)
-		ptep = find_current_mm_pte(mm->pgd, addr, NULL, NULL);
-	else
-		ptep = find_init_mm_pte(addr, NULL);
+	ptep = __find_linux_pte(mm->pgd, addr, NULL, &shift);
 	local_irq_restore(flags);
+
 	if (!ptep || pte_special(*ptep))
 		return ULONG_MAX;
+
+	if (shift > PAGE_SHIFT) {
+		unsigned long rpnmask = (1ul << shift) - PAGE_SIZE;
+
+		return pte_pfn(__pte(pte_val(*ptep) | (addr & rpnmask)));
+	}
+
 	return pte_pfn(*ptep);
 }
 
@@ -344,7 +350,7 @@ static const struct mce_derror_table mce_p9_derror_table[] = {
   MCE_INITIATOR_CPU,   MCE_SEV_SEVERE, true },
 { 0, false, 0, 0, 0, 0, 0 } };
 
-static int mce_find_instr_ea_and_pfn(struct pt_regs *regs, uint64_t *addr,
+static int mce_find_instr_ea_and_phys(struct pt_regs *regs, uint64_t *addr,
 					uint64_t *phys_addr)
 {
 	/*
@@ -541,7 +547,8 @@ static int mce_handle_derror(struct pt_regs *regs,
 			 * kernel/exception-64s.h
 			 */
 			if (get_paca()->in_mce < MAX_MCE_DEPTH)
-				mce_find_instr_ea_and_pfn(regs, addr, phys_addr);
+				mce_find_instr_ea_and_phys(regs, addr,
+							   phys_addr);
 		}
 		found = 1;
 	}
-- 
2.21.0


^ permalink raw reply related

* [PATCH v11 1/7] powerpc/mce: Schedule work from irq_work
From: Santosh Sivaraj @ 2019-08-20  8:13 UTC (permalink / raw)
  To: linuxppc-dev, Linux Kernel
  Cc: Aneesh Kumar K.V, Mahesh Salgaonkar, Nicholas Piggin,
	Mahesh Salgaonkar, Chandan Rajendra, stable, Reza Arbab
In-Reply-To: <20190820081352.8641-1-santosh@fossix.org>

schedule_work() cannot be called from MCE exception context as MCE can
interrupt even in interrupt disabled context.

fixes: 733e4a4c ("powerpc/mce: hookup memory_failure for UE errors")
Reviewed-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
Cc: stable@vger.kernel.org # v4.15+
---
 arch/powerpc/kernel/mce.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index b18df633eae9..cff31d4a501f 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -33,6 +33,7 @@ static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT],
 					mce_ue_event_queue);
 
 static void machine_check_process_queued_event(struct irq_work *work);
+static void machine_check_ue_irq_work(struct irq_work *work);
 void machine_check_ue_event(struct machine_check_event *evt);
 static void machine_process_ue_event(struct work_struct *work);
 
@@ -40,6 +41,10 @@ static struct irq_work mce_event_process_work = {
         .func = machine_check_process_queued_event,
 };
 
+static struct irq_work mce_ue_event_irq_work = {
+	.func = machine_check_ue_irq_work,
+};
+
 DECLARE_WORK(mce_ue_event_work, machine_process_ue_event);
 
 static void mce_set_error_info(struct machine_check_event *mce,
@@ -199,6 +204,10 @@ void release_mce_event(void)
 	get_mce_event(NULL, true);
 }
 
+static void machine_check_ue_irq_work(struct irq_work *work)
+{
+	schedule_work(&mce_ue_event_work);
+}
 
 /*
  * Queue up the MCE event which then can be handled later.
@@ -216,7 +225,7 @@ void machine_check_ue_event(struct machine_check_event *evt)
 	memcpy(this_cpu_ptr(&mce_ue_event_queue[index]), evt, sizeof(*evt));
 
 	/* Queue work to process this event later. */
-	schedule_work(&mce_ue_event_work);
+	irq_work_queue(&mce_ue_event_irq_work);
 }
 
 /*
-- 
2.21.0


^ permalink raw reply related


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox