* [RFC PATCH 2/4] powerpc/64e: Get esr offset with _ESR macro
From: sxwjean @ 2021-07-26 14:30 UTC (permalink / raw)
To: linuxppc-dev
Cc: ravi.bangoria, Xiongwei Song, aneesh.kumar, oleg, linux-kernel,
efremov, paulus, npiggin, peterx, akpm, sandipan
In-Reply-To: <20210726143053.532839-1-sxwjean@me.com>
From: Xiongwei Song <sxwjean@gmail.com>
Use _ESR to get the offset of esr register in pr_regs for 64e cpus.
Signed-off-by: Xiongwei Song <sxwjean@gmail.com>
---
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/kernel/exceptions-64e.S | 10 +++++-----
2 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index a47eefa09bcb..f4ebc435fd78 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -287,6 +287,7 @@ int main(void)
STACK_PT_REGS_OFFSET(_XER, xer);
STACK_PT_REGS_OFFSET(_DAR, dar);
STACK_PT_REGS_OFFSET(_DSISR, dsisr);
+ STACK_PT_REGS_OFFSET(_ESR, esr);
STACK_PT_REGS_OFFSET(ORIG_GPR3, orig_gpr3);
STACK_PT_REGS_OFFSET(RESULT, result);
STACK_PT_REGS_OFFSET(_TRAP, trap);
@@ -298,7 +299,6 @@ int main(void)
* we use them to hold SRR0 and SRR1.
*/
STACK_PT_REGS_OFFSET(_DEAR, dar);
- STACK_PT_REGS_OFFSET(_ESR, dsisr);
#else /* CONFIG_PPC64 */
STACK_PT_REGS_OFFSET(SOFTE, softe);
STACK_PT_REGS_OFFSET(_PPR, ppr);
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 1401787b0b93..bf8c4c2f98ea 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -546,7 +546,7 @@ __end_interrupts:
mfspr r14,SPRN_DEAR
mfspr r15,SPRN_ESR
std r14,_DAR(r1)
- std r15,_DSISR(r1)
+ std r15,_ESR(r1)
ld r14,PACA_EXGEN+EX_R14(r13)
ld r15,PACA_EXGEN+EX_R15(r13)
EXCEPTION_COMMON(0x300)
@@ -559,7 +559,7 @@ __end_interrupts:
li r15,0
mr r14,r10
std r14,_DAR(r1)
- std r15,_DSISR(r1)
+ std r15,_ESR(r1)
ld r14,PACA_EXGEN+EX_R14(r13)
ld r15,PACA_EXGEN+EX_R15(r13)
EXCEPTION_COMMON(0x400)
@@ -576,7 +576,7 @@ __end_interrupts:
mfspr r14,SPRN_DEAR
mfspr r15,SPRN_ESR
std r14,_DAR(r1)
- std r15,_DSISR(r1)
+ std r15,_ESR(r1)
ld r14,PACA_EXGEN+EX_R14(r13)
ld r15,PACA_EXGEN+EX_R15(r13)
EXCEPTION_COMMON(0x600)
@@ -587,7 +587,7 @@ __end_interrupts:
NORMAL_EXCEPTION_PROLOG(0x700, BOOKE_INTERRUPT_PROGRAM,
PROLOG_ADDITION_1REG)
mfspr r14,SPRN_ESR
- std r14,_DSISR(r1)
+ std r14,_ESR(r1)
ld r14,PACA_EXGEN+EX_R14(r13)
EXCEPTION_COMMON(0x700)
addi r3,r1,STACK_FRAME_OVERHEAD
@@ -1058,7 +1058,7 @@ bad_stack_book3e:
mfspr r10,SPRN_DEAR
mfspr r11,SPRN_ESR
std r10,_DAR(r1)
- std r11,_DSISR(r1)
+ std r11,_ESR(r1)
std r0,GPR0(r1); /* save r0 in stackframe */ \
std r2,GPR2(r1); /* save r2 in stackframe */ \
SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \
--
2.30.2
^ permalink raw reply related
* [RFC PATCH 3/4] powerpc: Optimize register usage for dear register
From: sxwjean @ 2021-07-26 14:30 UTC (permalink / raw)
To: linuxppc-dev
Cc: ravi.bangoria, Xiongwei Song, aneesh.kumar, oleg, linux-kernel,
efremov, paulus, npiggin, peterx, akpm, sandipan
In-Reply-To: <20210726143053.532839-1-sxwjean@me.com>
From: Xiongwei Song <sxwjean@gmail.com>
Create an anonymous union for dar and dear regsiters, we can reference
dear to get the effective address when CONFIG_4xx=y or CONFIG_BOOKE=y.
Otherwise, reference dar. This makes code more clear.
Signed-off-by: Xiongwei Song <sxwjean@gmail.com>
---
arch/powerpc/include/asm/ptrace.h | 5 ++++-
arch/powerpc/include/uapi/asm/ptrace.h | 5 ++++-
arch/powerpc/kernel/process.c | 2 +-
arch/powerpc/kernel/ptrace/ptrace.c | 2 ++
arch/powerpc/kernel/traps.c | 5 ++++-
arch/powerpc/mm/fault.c | 2 +-
6 files changed, 16 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index c252d04b1206..fa725e3238c2 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -43,7 +43,10 @@ struct pt_regs
unsigned long mq;
#endif
unsigned long trap;
- unsigned long dar;
+ union {
+ unsigned long dar;
+ unsigned long dear;
+ };
union {
unsigned long dsisr;
unsigned long esr;
diff --git a/arch/powerpc/include/uapi/asm/ptrace.h b/arch/powerpc/include/uapi/asm/ptrace.h
index e357288b5f34..9ae150fb4c4b 100644
--- a/arch/powerpc/include/uapi/asm/ptrace.h
+++ b/arch/powerpc/include/uapi/asm/ptrace.h
@@ -52,7 +52,10 @@ struct pt_regs
unsigned long trap; /* Reason for being here */
/* N.B. for critical exceptions on 4xx, the dar and dsisr
fields are overloaded to hold srr0 and srr1. */
- unsigned long dar; /* Fault registers */
+ union {
+ unsigned long dar; /* Fault registers */
+ unsigned long dear;
+ };
union {
unsigned long dsisr; /* on Book-S used for DSISR */
unsigned long esr; /* on 4xx/Book-E used for ESR */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index f74af8f9133c..50436b52c213 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1499,7 +1499,7 @@ static void __show_regs(struct pt_regs *regs)
trap == INTERRUPT_DATA_STORAGE ||
trap == INTERRUPT_ALIGNMENT) {
if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
- pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->esr);
+ pr_cont("DEAR: "REG" ESR: "REG" ", regs->dear, regs->esr);
else
pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
}
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 00789ad2c4a3..969dca8b0718 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -373,6 +373,8 @@ void __init pt_regs_check(void)
offsetof(struct user_pt_regs, trap));
BUILD_BUG_ON(offsetof(struct pt_regs, dar) !=
offsetof(struct user_pt_regs, dar));
+ BUILD_BUG_ON(offsetof(struct pt_regs, dear) !=
+ offsetof(struct user_pt_regs, dear));
BUILD_BUG_ON(offsetof(struct pt_regs, dsisr) !=
offsetof(struct user_pt_regs, dsisr));
BUILD_BUG_ON(offsetof(struct pt_regs, esr) !=
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 2164f5705a0b..0796630d3d23 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1609,7 +1609,10 @@ DEFINE_INTERRUPT_HANDLER(alignment_exception)
}
bad:
if (user_mode(regs))
- _exception(sig, regs, code, regs->dar);
+ if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
+ _exception(sig, regs, code, regs->dear);
+ else
+ _exception(sig, regs, code, regs->dar);
else
bad_page_fault(regs, sig);
}
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 62953d4e7c93..3db6b39a1178 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -542,7 +542,7 @@ static __always_inline void __do_page_fault(struct pt_regs *regs)
long err;
if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
- err = ___do_page_fault(regs, regs->dar, regs->esr);
+ err = ___do_page_fault(regs, regs->dear, regs->esr);
else
err = ___do_page_fault(regs, regs->dar, regs->dsisr);
--
2.30.2
^ permalink raw reply related
* [RFC PATCH 1/4] powerpc: Optimize register usage for esr register
From: sxwjean @ 2021-07-26 14:30 UTC (permalink / raw)
To: linuxppc-dev
Cc: ravi.bangoria, Xiongwei Song, aneesh.kumar, oleg, linux-kernel,
efremov, paulus, npiggin, peterx, akpm, sandipan
From: Xiongwei Song <sxwjean@gmail.com>
Create an anonymous union for dsisr and esr regsiters, we can reference
esr to get the exception detail when CONFIG_4xx=y or CONFIG_BOOKE=y.
Otherwise, reference dsisr. This makes code more clear.
Signed-off-by: Xiongwei Song <sxwjean@gmail.com>
---
arch/powerpc/include/asm/ptrace.h | 5 ++++-
arch/powerpc/include/uapi/asm/ptrace.h | 5 ++++-
arch/powerpc/kernel/process.c | 2 +-
arch/powerpc/kernel/ptrace/ptrace.c | 2 ++
arch/powerpc/kernel/traps.c | 2 +-
arch/powerpc/mm/fault.c | 16 ++++++++++++++--
arch/powerpc/platforms/44x/machine_check.c | 4 ++--
arch/powerpc/platforms/4xx/machine_check.c | 2 +-
8 files changed, 29 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 3e5d470a6155..c252d04b1206 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -44,7 +44,10 @@ struct pt_regs
#endif
unsigned long trap;
unsigned long dar;
- unsigned long dsisr;
+ union {
+ unsigned long dsisr;
+ unsigned long esr;
+ };
unsigned long result;
};
};
diff --git a/arch/powerpc/include/uapi/asm/ptrace.h b/arch/powerpc/include/uapi/asm/ptrace.h
index 7004cfea3f5f..e357288b5f34 100644
--- a/arch/powerpc/include/uapi/asm/ptrace.h
+++ b/arch/powerpc/include/uapi/asm/ptrace.h
@@ -53,7 +53,10 @@ struct pt_regs
/* N.B. for critical exceptions on 4xx, the dar and dsisr
fields are overloaded to hold srr0 and srr1. */
unsigned long dar; /* Fault registers */
- unsigned long dsisr; /* on 4xx/Book-E used for ESR */
+ union {
+ unsigned long dsisr; /* on Book-S used for DSISR */
+ unsigned long esr; /* on 4xx/Book-E used for ESR */
+ };
unsigned long result; /* Result of a system call */
};
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 185beb290580..f74af8f9133c 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1499,7 +1499,7 @@ static void __show_regs(struct pt_regs *regs)
trap == INTERRUPT_DATA_STORAGE ||
trap == INTERRUPT_ALIGNMENT) {
if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
- pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
+ pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->esr);
else
pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
}
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 0a0a33eb0d28..00789ad2c4a3 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -375,6 +375,8 @@ void __init pt_regs_check(void)
offsetof(struct user_pt_regs, dar));
BUILD_BUG_ON(offsetof(struct pt_regs, dsisr) !=
offsetof(struct user_pt_regs, dsisr));
+ BUILD_BUG_ON(offsetof(struct pt_regs, esr) !=
+ offsetof(struct user_pt_regs, esr));
BUILD_BUG_ON(offsetof(struct pt_regs, result) !=
offsetof(struct user_pt_regs, result));
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index dfbce527c98e..2164f5705a0b 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -562,7 +562,7 @@ static inline int check_io_access(struct pt_regs *regs)
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
/* On 4xx, the reason for the machine check or program exception
is in the ESR. */
-#define get_reason(regs) ((regs)->dsisr)
+#define get_reason(regs) ((regs)->esr)
#define REASON_FP ESR_FP
#define REASON_ILLEGAL (ESR_PIL | ESR_PUO)
#define REASON_PRIVILEGED ESR_PPR
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index a8d0ce85d39a..62953d4e7c93 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -541,7 +541,11 @@ static __always_inline void __do_page_fault(struct pt_regs *regs)
{
long err;
- err = ___do_page_fault(regs, regs->dar, regs->dsisr);
+ if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
+ err = ___do_page_fault(regs, regs->dar, regs->esr);
+ else
+ err = ___do_page_fault(regs, regs->dar, regs->dsisr);
+
if (unlikely(err))
bad_page_fault(regs, err);
}
@@ -567,7 +571,15 @@ NOKPROBE_SYMBOL(hash__do_page_fault);
*/
static void __bad_page_fault(struct pt_regs *regs, int sig)
{
- int is_write = page_fault_is_write(regs->dsisr);
+ unsigned long err_reg;
+ int is_write;
+
+ if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE))
+ err_reg = regs->esr;
+ else
+ err_reg = regs->dsisr;
+
+ is_write = page_fault_is_write(err_reg);
/* kernel has accessed a bad area */
diff --git a/arch/powerpc/platforms/44x/machine_check.c b/arch/powerpc/platforms/44x/machine_check.c
index a5c898bb9bab..5d19daacd78a 100644
--- a/arch/powerpc/platforms/44x/machine_check.c
+++ b/arch/powerpc/platforms/44x/machine_check.c
@@ -11,7 +11,7 @@
int machine_check_440A(struct pt_regs *regs)
{
- unsigned long reason = regs->dsisr;
+ unsigned long reason = regs->esr;
printk("Machine check in kernel mode.\n");
if (reason & ESR_IMCP){
@@ -48,7 +48,7 @@ int machine_check_440A(struct pt_regs *regs)
#ifdef CONFIG_PPC_47x
int machine_check_47x(struct pt_regs *regs)
{
- unsigned long reason = regs->dsisr;
+ unsigned long reason = regs->esr;
u32 mcsr;
printk(KERN_ERR "Machine check in kernel mode.\n");
diff --git a/arch/powerpc/platforms/4xx/machine_check.c b/arch/powerpc/platforms/4xx/machine_check.c
index a71c29892a91..a905da1d6f41 100644
--- a/arch/powerpc/platforms/4xx/machine_check.c
+++ b/arch/powerpc/platforms/4xx/machine_check.c
@@ -10,7 +10,7 @@
int machine_check_4xx(struct pt_regs *regs)
{
- unsigned long reason = regs->dsisr;
+ unsigned long reason = regs->esr;
if (reason & ESR_IMCP) {
printk("Instruction");
--
2.30.2
^ permalink raw reply related
* [PATCH] powerpc/stacktrace: Include linux/delay.h
From: Michal Suchanek @ 2021-07-26 15:42 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Michal Suchanek
commit 7c6986ade69e ("powerpc/stacktrace: Fix spurious "stale" traces in raise_backtrace_ipi()")
introduces udelay() call without including the linux/delay.h header.
This may happen to work on master but the header that declares the
functionshould be included nonetheless.
Fixes: 7c6986ade69e ("powerpc/stacktrace: Fix spurious "stale" traces in raise_backtrace_ipi()")
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
---
arch/powerpc/kernel/stacktrace.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 2b0d04a1b7d2..a17ac10f86b1 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -12,6 +12,7 @@
#include <linux/kallsyms.h>
#include <linux/module.h>
#include <linux/nmi.h>
+#include <linux/delay.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
--
2.26.2
^ permalink raw reply related
* [PATCH] cpufreq:powernv: Fix init_chip_info initialization in numa=off
From: Pratik R. Sampat @ 2021-07-26 17:07 UTC (permalink / raw)
To: mpe, rjw, linux-pm, linuxppc-dev, linux-kernel, stable, psampat,
pratik.r.sampat
In the numa=off kernel command-line configuration init_chip_info() loops
around the number of chips and attempts to copy the cpumask of that node
which is NULL for all iterations after the first chip.
Hence, store the cpu mask for each chip instead of derving cpumask from
node while populating the "chips" struct array and copy that to the
chips[i].mask
Cc: stable@vger.kernel.org
Fixes: 053819e0bf84 ("cpufreq: powernv: Handle throttling due to Pmax capping at chip level")
Signed-off-by: Pratik R. Sampat <psampat@linux.ibm.com>
Reported-by: Shirisha Ganta <shirisha.ganta1@ibm.com>
---
drivers/cpufreq/powernv-cpufreq.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 005600cef273..8ec10d9aed8f 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -1046,12 +1046,20 @@ static int init_chip_info(void)
unsigned int *chip;
unsigned int cpu, i;
unsigned int prev_chip_id = UINT_MAX;
+ cpumask_t *chip_cpu_mask;
int ret = 0;
chip = kcalloc(num_possible_cpus(), sizeof(*chip), GFP_KERNEL);
if (!chip)
return -ENOMEM;
+ /* Allocate a chip cpu mask large enough to fit mask for all chips */
+ chip_cpu_mask = kcalloc(32, sizeof(cpumask_t), GFP_KERNEL);
+ if (!chip_cpu_mask) {
+ ret = -ENOMEM;
+ goto free_and_return;
+ }
+
for_each_possible_cpu(cpu) {
unsigned int id = cpu_to_chip_id(cpu);
@@ -1059,22 +1067,25 @@ static int init_chip_info(void)
prev_chip_id = id;
chip[nr_chips++] = id;
}
+ cpumask_set_cpu(cpu, &chip_cpu_mask[nr_chips-1]);
}
chips = kcalloc(nr_chips, sizeof(struct chip), GFP_KERNEL);
if (!chips) {
ret = -ENOMEM;
- goto free_and_return;
+ goto out_chip_cpu_mask;
}
for (i = 0; i < nr_chips; i++) {
chips[i].id = chip[i];
- cpumask_copy(&chips[i].mask, cpumask_of_node(chip[i]));
+ cpumask_copy(&chips[i].mask, &chip_cpu_mask[i]);
INIT_WORK(&chips[i].throttle, powernv_cpufreq_work_fn);
for_each_cpu(cpu, &chips[i].mask)
per_cpu(chip_info, cpu) = &chips[i];
}
+out_chip_cpu_mask:
+ kfree(chip_cpu_mask);
free_and_return:
kfree(chip);
return ret;
--
2.31.1
^ permalink raw reply related
* Re: [PATCH] powerpc/stacktrace: Include linux/delay.h
From: Gabriel Paubert @ 2021-07-26 16:55 UTC (permalink / raw)
To: Michal Suchanek; +Cc: linuxppc-dev
In-Reply-To: <20210726154243.29025-1-msuchanek@suse.de>
On Mon, Jul 26, 2021 at 05:42:43PM +0200, Michal Suchanek wrote:
> commit 7c6986ade69e ("powerpc/stacktrace: Fix spurious "stale" traces in raise_backtrace_ipi()")
> introduces udelay() call without including the linux/delay.h header.
> This may happen to work on master but the header that declares the
> functionshould be included nonetheless.
>
> Fixes: 7c6986ade69e ("powerpc/stacktrace: Fix spurious "stale" traces in raise_backtrace_ipi()")
> Signed-off-by: Michal Suchanek <msuchanek@suse.de>
> ---
> arch/powerpc/kernel/stacktrace.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
> index 2b0d04a1b7d2..a17ac10f86b1 100644
> --- a/arch/powerpc/kernel/stacktrace.c
> +++ b/arch/powerpc/kernel/stacktrace.c
> @@ -12,6 +12,7 @@
> #include <linux/kallsyms.h>
> #include <linux/module.h>
> #include <linux/nmi.h>
> +#include <linux/delay.h>
> #include <linux/sched.h>
> #include <linux/sched/debug.h>
> #include <linux/sched/task_stack.h>
Hmm, I believe we try to keep the list of includes sorted in
alphabetical order.
Gabriel
^ permalink raw reply
* [PATCH v5 0/2] KVM: PPC: Book3S HV: Nested guest state sanitising changes
From: Fabiano Rosas @ 2021-07-26 20:17 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, npiggin
This series aims to stop contaminating the l2_hv structure with bits
that might have come from L1 state.
Patch 1 makes l2_hv read-only (mostly). It is now only changed when we
explicitly want to pass information to L1.
Patch 2 makes sure that L1 is not forwarded HFU interrupts when the
host has decided to disable any facilities (theoretical for now, since
HFSCR bits are always the same between L1/Ln).
Changes since v4:
- moved setting of the Cause bits under BOOK3S_INTERRUPT_H_FAC_UNAVAIL.
v4:
- now passing lpcr separately into load_l2_hv_regs to solve the
conflict with commit a19b70abc69a ("KVM: PPC: Book3S HV: Nested move
LPCR sanitising to sanitise_hv_regs");
- patch 2 now forwards a HEAI instead of injecting a Program.
https://lkml.kernel.org/r/20210722221240.2384655-1-farosas@linux.ibm.com
v3:
- removed the sanitise functions;
- moved the entry code into a new load_l2_hv_regs and the exit code
into the existing save_hv_return_state;
- new patch: removes the cause bits when L0 has disabled the
corresponding facility.
https://lkml.kernel.org/r/20210415230948.3563415-1-farosas@linux.ibm.com
v2:
- made the change more generic, not only applies to hfscr anymore;
- sanitisation is now done directly on the vcpu struct, l2_hv is left
unchanged.
https://lkml.kernel.org/r/20210406214645.3315819-1-farosas@linux.ibm.com
v1:
https://lkml.kernel.org/r/20210305231055.2913892-1-farosas@linux.ibm.com
Fabiano Rosas (2):
KVM: PPC: Book3S HV: Sanitise vcpu registers in nested path
KVM: PPC: Book3S HV: Stop forwarding all HFUs to L1
arch/powerpc/kvm/book3s_hv_nested.c | 118 ++++++++++++++++------------
1 file changed, 68 insertions(+), 50 deletions(-)
--
2.29.2
^ permalink raw reply
* [PATCH v5 1/2] KVM: PPC: Book3S HV: Sanitise vcpu registers in nested path
From: Fabiano Rosas @ 2021-07-26 20:17 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, npiggin
In-Reply-To: <20210726201710.2432874-1-farosas@linux.ibm.com>
As one of the arguments of the H_ENTER_NESTED hypercall, the nested
hypervisor (L1) prepares a structure containing the values of various
hypervisor-privileged registers with which it wants the nested guest
(L2) to run. Since the nested HV runs in supervisor mode it needs the
host to write to these registers.
To stop a nested HV manipulating this mechanism and using a nested
guest as a proxy to access a facility that has been made unavailable
to it, we have a routine that sanitises the values of the HV registers
before copying them into the nested guest's vcpu struct.
However, when coming out of the guest the values are copied as they
were back into L1 memory, which means that any sanitisation we did
during guest entry will be exposed to L1 after H_ENTER_NESTED returns.
This patch alters this sanitisation to have effect on the vcpu->arch
registers directly before entering and after exiting the guest,
leaving the structure that is copied back into L1 unchanged (except
when we really want L1 to access the value, e.g the Cause bits of
HFSCR).
Signed-off-by: Fabiano Rosas <farosas@linux.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_nested.c | 94 ++++++++++++++---------------
1 file changed, 46 insertions(+), 48 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 8543ad538b0c..8215dbd4be9a 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -105,7 +105,6 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
struct kvmppc_vcore *vc = vcpu->arch.vcore;
hr->dpdes = vc->dpdes;
- hr->hfscr = vcpu->arch.hfscr;
hr->purr = vcpu->arch.purr;
hr->spurr = vcpu->arch.spurr;
hr->ic = vcpu->arch.ic;
@@ -128,55 +127,17 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
case BOOK3S_INTERRUPT_H_INST_STORAGE:
hr->asdr = vcpu->arch.fault_gpa;
break;
+ case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+ hr->hfscr = ((~HFSCR_INTR_CAUSE & hr->hfscr) |
+ (HFSCR_INTR_CAUSE & vcpu->arch.hfscr));
+ break;
case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
hr->heir = vcpu->arch.emul_inst;
break;
}
}
-/*
- * This can result in some L0 HV register state being leaked to an L1
- * hypervisor when the hv_guest_state is copied back to the guest after
- * being modified here.
- *
- * There is no known problem with such a leak, and in many cases these
- * register settings could be derived by the guest by observing behaviour
- * and timing, interrupts, etc., but it is an issue to consider.
- */
-static void sanitise_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
-{
- struct kvmppc_vcore *vc = vcpu->arch.vcore;
- u64 mask;
-
- /*
- * Don't let L1 change LPCR bits for the L2 except these:
- */
- mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
- LPCR_LPES | LPCR_MER;
-
- /*
- * Additional filtering is required depending on hardware
- * and configuration.
- */
- hr->lpcr = kvmppc_filter_lpcr_hv(vcpu->kvm,
- (vc->lpcr & ~mask) | (hr->lpcr & mask));
-
- /*
- * Don't let L1 enable features for L2 which we've disabled for L1,
- * but preserve the interrupt cause field.
- */
- hr->hfscr &= (HFSCR_INTR_CAUSE | vcpu->arch.hfscr);
-
- /* Don't let data address watchpoint match in hypervisor state */
- hr->dawrx0 &= ~DAWRX_HYP;
- hr->dawrx1 &= ~DAWRX_HYP;
-
- /* Don't let completed instruction address breakpt match in HV state */
- if ((hr->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
- hr->ciabr &= ~CIABR_PRIV;
-}
-
-static void restore_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr)
+static void restore_hv_regs(struct kvm_vcpu *vcpu, const struct hv_guest_state *hr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -288,6 +249,43 @@ static int kvmhv_write_guest_state_and_regs(struct kvm_vcpu *vcpu,
sizeof(struct pt_regs));
}
+static void load_l2_hv_regs(struct kvm_vcpu *vcpu,
+ const struct hv_guest_state *l2_hv,
+ const struct hv_guest_state *l1_hv, u64 *lpcr)
+{
+ struct kvmppc_vcore *vc = vcpu->arch.vcore;
+ u64 mask;
+
+ restore_hv_regs(vcpu, l2_hv);
+
+ /*
+ * Don't let L1 change LPCR bits for the L2 except these:
+ */
+ mask = LPCR_DPFD | LPCR_ILE | LPCR_TC | LPCR_AIL | LPCR_LD |
+ LPCR_LPES | LPCR_MER;
+
+ /*
+ * Additional filtering is required depending on hardware
+ * and configuration.
+ */
+ *lpcr = kvmppc_filter_lpcr_hv(vcpu->kvm,
+ (vc->lpcr & ~mask) | (*lpcr & mask));
+
+ /*
+ * Don't let L1 enable features for L2 which we've disabled for L1,
+ * but preserve the interrupt cause field.
+ */
+ vcpu->arch.hfscr = l2_hv->hfscr & (HFSCR_INTR_CAUSE | l1_hv->hfscr);
+
+ /* Don't let data address watchpoint match in hypervisor state */
+ vcpu->arch.dawrx0 = l2_hv->dawrx0 & ~DAWRX_HYP;
+ vcpu->arch.dawrx1 = l2_hv->dawrx1 & ~DAWRX_HYP;
+
+ /* Don't let completed instruction address breakpt match in HV state */
+ if ((l2_hv->ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
+ vcpu->arch.ciabr = l2_hv->ciabr & ~CIABR_PRIV;
+}
+
long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
{
long int err, r;
@@ -296,7 +294,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
struct hv_guest_state l2_hv = {0}, saved_l1_hv;
struct kvmppc_vcore *vc = vcpu->arch.vcore;
u64 hv_ptr, regs_ptr;
- u64 hdec_exp;
+ u64 hdec_exp, lpcr;
s64 delta_purr, delta_spurr, delta_ic, delta_vtb;
if (vcpu->kvm->arch.l1_ptcr == 0)
@@ -349,8 +347,8 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
/* Guest must always run with ME enabled, HV disabled. */
vcpu->arch.shregs.msr = (vcpu->arch.regs.msr | MSR_ME) & ~MSR_HV;
- sanitise_hv_regs(vcpu, &l2_hv);
- restore_hv_regs(vcpu, &l2_hv);
+ lpcr = l2_hv.lpcr;
+ load_l2_hv_regs(vcpu, &l2_hv, &saved_l1_hv, &lpcr);
vcpu->arch.ret = RESUME_GUEST;
vcpu->arch.trap = 0;
@@ -360,7 +358,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
r = RESUME_HOST;
break;
}
- r = kvmhv_run_single_vcpu(vcpu, hdec_exp, l2_hv.lpcr);
+ r = kvmhv_run_single_vcpu(vcpu, hdec_exp, lpcr);
} while (is_kvmppc_resume_guest(r));
/* save L2 state for return */
--
2.29.2
^ permalink raw reply related
* [PATCH v5 2/2] KVM: PPC: Book3S HV: Stop forwarding all HFUs to L1
From: Fabiano Rosas @ 2021-07-26 20:17 UTC (permalink / raw)
To: kvm-ppc; +Cc: linuxppc-dev, npiggin
In-Reply-To: <20210726201710.2432874-1-farosas@linux.ibm.com>
If the nested hypervisor has no access to a facility because it has
been disabled by the host, it should also not be able to see the
Hypervisor Facility Unavailable that arises from one of its guests
trying to access the facility.
This patch turns a HFU that happened in L2 into a Hypervisor Emulation
Assistance interrupt and forwards it to L1 for handling. The ones that
happened because L1 explicitly disabled the facility for L2 are still
let through, along with the corresponding Cause bits in the HFSCR.
Signed-off-by: Fabiano Rosas <farosas@linux.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/kvm/book3s_hv_nested.c | 32 +++++++++++++++++++++++------
1 file changed, 26 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 8215dbd4be9a..d544b092b49a 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -99,7 +99,7 @@ static void byteswap_hv_regs(struct hv_guest_state *hr)
hr->dawrx1 = swab64(hr->dawrx1);
}
-static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
+static void save_hv_return_state(struct kvm_vcpu *vcpu,
struct hv_guest_state *hr)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -118,7 +118,7 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
hr->pidr = vcpu->arch.pid;
hr->cfar = vcpu->arch.cfar;
hr->ppr = vcpu->arch.ppr;
- switch (trap) {
+ switch (vcpu->arch.trap) {
case BOOK3S_INTERRUPT_H_DATA_STORAGE:
hr->hdar = vcpu->arch.fault_dar;
hr->hdsisr = vcpu->arch.fault_dsisr;
@@ -128,9 +128,29 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
hr->asdr = vcpu->arch.fault_gpa;
break;
case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
- hr->hfscr = ((~HFSCR_INTR_CAUSE & hr->hfscr) |
- (HFSCR_INTR_CAUSE & vcpu->arch.hfscr));
- break;
+ {
+ u8 cause = vcpu->arch.hfscr >> 56;
+
+ WARN_ON_ONCE(cause >= BITS_PER_LONG);
+
+ if (!(hr->hfscr & (1UL << cause))) {
+ hr->hfscr = ((~HFSCR_INTR_CAUSE & hr->hfscr) |
+ (HFSCR_INTR_CAUSE & vcpu->arch.hfscr));
+ break;
+ }
+
+ /*
+ * We have disabled this facility, so it does not
+ * exist from L1's perspective. Turn it into a HEAI.
+ */
+ vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST;
+ kvmppc_load_last_inst(vcpu, INST_GENERIC, &vcpu->arch.emul_inst);
+
+ /* Don't leak the cause field */
+ hr->hfscr &= ~HFSCR_INTR_CAUSE;
+
+ fallthrough;
+ }
case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
hr->heir = vcpu->arch.emul_inst;
break;
@@ -368,7 +388,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
delta_spurr = vcpu->arch.spurr - l2_hv.spurr;
delta_ic = vcpu->arch.ic - l2_hv.ic;
delta_vtb = vc->vtb - l2_hv.vtb;
- save_hv_return_state(vcpu, vcpu->arch.trap, &l2_hv);
+ save_hv_return_state(vcpu, &l2_hv);
/* restore L1 state */
vcpu->arch.nested = NULL;
--
2.29.2
^ permalink raw reply related
* RE: [PATCH v3] soc: fsl: qe: convert QE interrupt controller to platform_device
From: Leo Li @ 2021-07-26 20:44 UTC (permalink / raw)
To: Maxim Kochetkov, linuxppc-dev@lists.ozlabs.org
Cc: kernel test robot, saravanak@google.com,
gregkh@linuxfoundation.org, linux-kernel@vger.kernel.org,
Dan Carpenter, linux-arm-kernel@lists.infradead.org, Qiang Zhao
In-Reply-To: <20210726052217.13558-1-fido_max@inbox.ru>
> -----Original Message-----
> From: Maxim Kochetkov <fido_max@inbox.ru>
> Sent: Monday, July 26, 2021 12:22 AM
> To: linuxppc-dev@lists.ozlabs.org
> Cc: linux-arm-kernel@lists.infradead.org; linux-kernel@vger.kernel.org;
> saravanak@google.com; Leo Li <leoyang.li@nxp.com>; Qiang Zhao
> <qiang.zhao@nxp.com>; gregkh@linuxfoundation.org; Maxim Kochetkov
> <fido_max@inbox.ru>; kernel test robot <lkp@intel.com>; Dan Carpenter
> <dan.carpenter@oracle.com>
> Subject: [PATCH v3] soc: fsl: qe: convert QE interrupt controller to
> platform_device
>
> Since 5.13 QE's ucc nodes can't get interrupts from devicetree:
>
> ucc@2000 {
> cell-index = <1>;
> reg = <0x2000 0x200>;
> interrupts = <32>;
> interrupt-parent = <&qeic>;
> };
>
> Now fw_devlink expects driver to create and probe a struct device for
> interrupt controller.
>
> So lets convert this driver to simple platform_device with probe().
> Also use platform_get_ and devm_ family function to get/allocate resources
> and drop unused .compatible = "qeic".
>
> [1] -
> https://eur01.safelinks.protection.outlook.com/?url=https%3A%2F%2Flore.k
> ernel.org%2Flkml%2FCAGETcx9PiX%3D%3DmLxB9PO8Myyk6u2vhPVwTMsA
> 5NkD-
> ywH5xhusw%40mail.gmail.com&data=04%7C01%7Cleoyang.li%40nxp.co
> m%7C6e64e4b86f2d4a89390808d94ff50bec%7C686ea1d3bc2b4c6fa92cd99c5c
> 301635%7C0%7C0%7C637628736153046082%7CUnknown%7CTWFpbGZsb3d8
> eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3
> D%7C1000&sdata=G7HhGFmRLvMyNMULSddWctD3HhtVWMfZAxPXjl8
> CBTY%3D&reserved=0
> Fixes: e590474768f1 ("driver core: Set fw_devlink=on by default")
> Fixes: ea718c699055 ("Revert "Revert "driver core: Set fw_devlink=on by
> default""")
> Signed-off-by: Maxim Kochetkov <fido_max@inbox.ru>
> Reported-by: kernel test robot <lkp@intel.com>
> Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
> ---
> Changes in v3:
> - use .compatible = "qeic" again (Li Yang <leoyang.li@nxp.com> asks to keep
> it)
>
> Changes in v2:
> - use devm_ family functions to allocate mem/resources
> - use platform_get_ family functions to get resources/irqs
> - drop unused .compatible = "qeic"
>
> drivers/soc/fsl/qe/qe_ic.c | 75 ++++++++++++++++++++++----------------
> 1 file changed, 44 insertions(+), 31 deletions(-)
>
> diff --git a/drivers/soc/fsl/qe/qe_ic.c b/drivers/soc/fsl/qe/qe_ic.c index
> 3f711c1a0996..54cabd2605dd 100644
> --- a/drivers/soc/fsl/qe/qe_ic.c
> +++ b/drivers/soc/fsl/qe/qe_ic.c
> @@ -23,6 +23,7 @@
> #include <linux/signal.h>
> #include <linux/device.h>
> #include <linux/spinlock.h>
> +#include <linux/platform_device.h>
> #include <asm/irq.h>
> #include <asm/io.h>
> #include <soc/fsl/qe/qe.h>
> @@ -404,41 +405,40 @@ static void qe_ic_cascade_muxed_mpic(struct
> irq_desc *desc)
> chip->irq_eoi(&desc->irq_data);
> }
>
> -static void __init qe_ic_init(struct device_node *node)
> +static int qe_ic_init(struct platform_device *pdev)
> {
> + struct device *dev = &pdev->dev;
> void (*low_handler)(struct irq_desc *desc);
> void (*high_handler)(struct irq_desc *desc);
> struct qe_ic *qe_ic;
> - struct resource res;
> - u32 ret;
> + struct resource *res;
> + struct device_node *node = pdev->dev.of_node;
>
> - ret = of_address_to_resource(node, 0, &res);
> - if (ret)
> - return;
> + res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
> + if (res == NULL) {
> + dev_err(dev, "no memory resource defined\n");
> + return -ENODEV;
> + }
>
> - qe_ic = kzalloc(sizeof(*qe_ic), GFP_KERNEL);
> + qe_ic = devm_kzalloc(dev, sizeof(*qe_ic), GFP_KERNEL);
> if (qe_ic == NULL)
> - return;
> + return -ENOMEM;
>
> - qe_ic->irqhost = irq_domain_add_linear(node, NR_QE_IC_INTS,
> - &qe_ic_host_ops, qe_ic);
> - if (qe_ic->irqhost == NULL) {
> - kfree(qe_ic);
> - return;
> + qe_ic->regs = devm_ioremap(dev, res->start, resource_size(res));
> + if (qe_ic->regs == NULL) {
> + dev_err(dev, "failed to ioremap() registers\n");
> + return -ENODEV;
> }
>
> - qe_ic->regs = ioremap(res.start, resource_size(&res));
> -
> qe_ic->hc_irq = qe_ic_irq_chip;
>
> - qe_ic->virq_high = irq_of_parse_and_map(node, 0);
> - qe_ic->virq_low = irq_of_parse_and_map(node, 1);
> + qe_ic->virq_high = platform_get_irq(pdev, 0);
> + qe_ic->virq_low = platform_get_irq(pdev, 1);
>
> - if (!qe_ic->virq_low) {
> - printk(KERN_ERR "Failed to map QE_IC low IRQ\n");
> - kfree(qe_ic);
> - return;
> + if (qe_ic->virq_low < 0) {
> + return -ENODEV;
> }
> +
> if (qe_ic->virq_high != qe_ic->virq_low) {
> low_handler = qe_ic_cascade_low;
> high_handler = qe_ic_cascade_high;
> @@ -447,6 +447,13 @@ static void __init qe_ic_init(struct device_node
> *node)
> high_handler = NULL;
> }
>
> + qe_ic->irqhost = irq_domain_add_linear(node, NR_QE_IC_INTS,
> + &qe_ic_host_ops, qe_ic);
> + if (qe_ic->irqhost == NULL) {
> + dev_err(dev, "failed to add irq domain\n");
> + return -ENODEV;
> + }
> +
> qe_ic_write(qe_ic->regs, QEIC_CICR, 0);
>
> irq_set_handler_data(qe_ic->virq_low, qe_ic); @@ -456,20 +463,26
> @@ static void __init qe_ic_init(struct device_node *node)
> irq_set_handler_data(qe_ic->virq_high, qe_ic);
> irq_set_chained_handler(qe_ic->virq_high, high_handler);
> }
> + return 0;
> }
> +static const struct of_device_id qe_ic_ids[] = {
> + { .compatible = "fsl,qe-ic"},
> + { .compatible = "qeic"},
Probably you missed the point from my first response. The original code is match by device type "qeic" instead of compatible string "qeic". So we should use { .type = "qeic"} here.
> + {},
> +};
>
> -static int __init qe_ic_of_init(void)
> +static struct platform_driver qe_ic_driver =
> {
> - struct device_node *np;
> + .driver = {
> + .name = "qe-ic",
> + .of_match_table = qe_ic_ids,
> + },
> + .probe = qe_ic_init,
> +};
>
> - np = of_find_compatible_node(NULL, NULL, "fsl,qe-ic");
> - if (!np) {
> - np = of_find_node_by_type(NULL, "qeic");
> - if (!np)
> - return -ENODEV;
> - }
> - qe_ic_init(np);
> - of_node_put(np);
> +static int __init qe_ic_of_init(void)
> +{
> + platform_driver_register(&qe_ic_driver);
> return 0;
> }
> subsys_initcall(qe_ic_of_init);
> --
> 2.31.1
^ permalink raw reply
* Re: Linux kernel: powerpc: KVM guest to host memory corruption
From: Michael Ellerman @ 2021-07-27 0:46 UTC (permalink / raw)
To: oss-security; +Cc: linuxppc-dev
In-Reply-To: <87im0x1lqi.fsf@mpe.ellerman.id.au>
Michael Ellerman <mpe@ellerman.id.au> writes:
> The Linux kernel for powerpc since v3.10 has a bug which allows a malicious KVM guest to
> corrupt host memory.
>
> In the handling of the H_RTAS hypercall, args.rets is made to point into the args.args
> buffer which is located on the stack:
>
> args.rets = &args.args[be32_to_cpu(args.nargs)];
>
> However args.nargs has not been range checked. That allows the guest to point args.rets
> anywhere up to +16GB from args.args.
>
> The guest does not have control of what is written to args.rets, it is always (u32)-3,
> because subsequent code does check nargs. Additionally the guest will be killed as a
> result of the nargs being out of range, so a given guest only has a single shot at
> corrupting memory.
>
> Only machines using Linux as the hypervisor, aka. KVM or bare metal, are affected by the
> bug.
>
> The bug was introduced in:
>
> 8e591cb72047 ("KVM: PPC: Book3S: Add infrastructure to implement kernel-side RTAS calls")
>
> Which was first released in v3.10.
>
> The upstream fix is:
>
> f62f3c20647e ("KVM: PPC: Book3S: Fix H_RTAS rets buffer overflow")
>
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=f62f3c20647ebd5fb6ecb8f0b477b9281c44c10a
>
> Which will be included in the v5.14 release.
This has been assigned CVE-2021-37576.
cheers
^ permalink raw reply
* Re: [PATCH v5 2/2] KVM: PPC: Book3S HV: Stop forwarding all HFUs to L1
From: Nicholas Piggin @ 2021-07-27 3:09 UTC (permalink / raw)
To: Fabiano Rosas, kvm-ppc; +Cc: linuxppc-dev
In-Reply-To: <20210726201710.2432874-3-farosas@linux.ibm.com>
Excerpts from Fabiano Rosas's message of July 27, 2021 6:17 am:
> If the nested hypervisor has no access to a facility because it has
> been disabled by the host, it should also not be able to see the
> Hypervisor Facility Unavailable that arises from one of its guests
> trying to access the facility.
>
> This patch turns a HFU that happened in L2 into a Hypervisor Emulation
> Assistance interrupt and forwards it to L1 for handling. The ones that
> happened because L1 explicitly disabled the facility for L2 are still
> let through, along with the corresponding Cause bits in the HFSCR.
>
> Signed-off-by: Fabiano Rosas <farosas@linux.ibm.com>
> Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
> ---
> arch/powerpc/kvm/book3s_hv_nested.c | 32 +++++++++++++++++++++++------
> 1 file changed, 26 insertions(+), 6 deletions(-)
>
> diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
> index 8215dbd4be9a..d544b092b49a 100644
> --- a/arch/powerpc/kvm/book3s_hv_nested.c
> +++ b/arch/powerpc/kvm/book3s_hv_nested.c
> @@ -99,7 +99,7 @@ static void byteswap_hv_regs(struct hv_guest_state *hr)
> hr->dawrx1 = swab64(hr->dawrx1);
> }
>
> -static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
> +static void save_hv_return_state(struct kvm_vcpu *vcpu,
> struct hv_guest_state *hr)
> {
> struct kvmppc_vcore *vc = vcpu->arch.vcore;
> @@ -118,7 +118,7 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
> hr->pidr = vcpu->arch.pid;
> hr->cfar = vcpu->arch.cfar;
> hr->ppr = vcpu->arch.ppr;
> - switch (trap) {
> + switch (vcpu->arch.trap) {
> case BOOK3S_INTERRUPT_H_DATA_STORAGE:
> hr->hdar = vcpu->arch.fault_dar;
> hr->hdsisr = vcpu->arch.fault_dsisr;
> @@ -128,9 +128,29 @@ static void save_hv_return_state(struct kvm_vcpu *vcpu, int trap,
> hr->asdr = vcpu->arch.fault_gpa;
> break;
> case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
> - hr->hfscr = ((~HFSCR_INTR_CAUSE & hr->hfscr) |
> - (HFSCR_INTR_CAUSE & vcpu->arch.hfscr));
> - break;
> + {
> + u8 cause = vcpu->arch.hfscr >> 56;
Can this be u64 just to help gcc?
> +
> + WARN_ON_ONCE(cause >= BITS_PER_LONG);
> +
> + if (!(hr->hfscr & (1UL << cause))) {
> + hr->hfscr = ((~HFSCR_INTR_CAUSE & hr->hfscr) |
> + (HFSCR_INTR_CAUSE & vcpu->arch.hfscr));
> + break;
> + }
> +
> + /*
> + * We have disabled this facility, so it does not
> + * exist from L1's perspective. Turn it into a HEAI.
> + */
> + vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST;
> + kvmppc_load_last_inst(vcpu, INST_GENERIC, &vcpu->arch.emul_inst);
Hmm, this doesn't handle kvmpc_load_last_inst failure. Other code tends
to just resume guest and retry in this case. Can we do that here?
> +
> + /* Don't leak the cause field */
> + hr->hfscr &= ~HFSCR_INTR_CAUSE;
This hunk also remains -- shouldn't change HFSCR for HEA, only HFAC.
Thanks,
Nick
^ permalink raw reply
* Re: [PATCH v5 4/6] powerpc/pseries: Consolidate different NUMA distance update code paths
From: Aneesh Kumar K.V @ 2021-07-27 3:32 UTC (permalink / raw)
To: David Gibson; +Cc: Nathan Lynch, Daniel Henrique Barboza, linuxppc-dev
In-Reply-To: <YP4f7lj9p4f/h77f@yekko>
David Gibson <david@gibson.dropbear.id.au> writes:
> On Thu, Jul 22, 2021 at 12:37:46PM +0530, Aneesh Kumar K.V wrote:
>> David Gibson <david@gibson.dropbear.id.au> writes:
>>
>> > On Mon, Jun 28, 2021 at 08:41:15PM +0530, Aneesh Kumar K.V wrote:
....
>
>> >
>> >> + nid = of_read_number(&aa.arrays[index], 1);
>> >> +
>> >> + if (nid == 0xffff || nid >= nr_node_ids)
>> >> + nid = default_nid;
>> >> + if (nid > 0 && affinity_form == FORM1_AFFINITY) {
>> >> + int i;
>> >> + const __be32 *associativity;
>> >> +
>> >> + index = lmb->aa_index * aa.array_sz;
>> >> + associativity = &aa.arrays[index];
>> >> + /*
>> >> + * lookup array associativity entries have different format
>> >> + * There is no length of the array as the first element.
>> >
>> > The difference it very small, and this is not a hot path. Couldn't
>> > you reduce a chunk of code by prepending aa.array_sz, then re-using
>> > __initialize_form1_numa_distance. Or even making
>> > __initialize_form1_numa_distance() take the length as a parameter.
>>
>> The changes are small but confusing w.r.t how we look at the
>> associativity-lookup-arrays. The way we interpret associativity array
>> and associativity lookup array using primary_domain_index is different.
>> Hence the '-1' in the node lookup here.
>
> They're really not, though. It's exactly the same interpretation of
> the associativity array itself - it's just that one of them has the
> array prepended with a (redundant) length. So you can make
> __initialize_form1_numa_distance() work on the "bare" associativity
> array, with a given length. Here you call it with aa.array_sz as the
> length, and in the other place you call it with prop[0] as the length.
>
>>
>> index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
>> nid = of_read_number(&aa.arrays[index], 1);
>>
>>
>> >
>> >> + */
>> >> + for (i = 0; i < max_associativity_domain_index; i++) {
>> >> + const __be32 *entry;
>> >> +
>> >> + entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
>> >
>> > Does anywhere verify that distance_ref_points[i] <= aa.array_size for
>> > every i?
>>
>> We do check for
>>
>> if (primary_domain_index <= aa.array_sz &&
>
> Right, but that doesn't check the other distance_ref_points entries.
> Not that there's any reason to have extra entries with Form2, but we
> still don't want stray array accesses.
This is how the change looks. I am not convinced this makes it simpler.
I will add that as the last patch and we can drop that if we find that
not helpful?
modified arch/powerpc/mm/numa.c
@@ -171,20 +171,31 @@ static void unmap_cpu_from_node(unsigned long cpu)
}
#endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
-/*
- * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
- * info is found.
- */
-static int associativity_to_nid(const __be32 *associativity)
+static int __associativity_to_nid(const __be32 *associativity,
+ bool lookup_array_assoc,
+ int max_array_index)
{
int nid = NUMA_NO_NODE;
+ int index;
if (!numa_enabled)
goto out;
+ /*
+ * ibm,associativity-lookup-array doesn't have element
+ * count at the start of the associativity. Hence
+ * decrement the primary_domain_index when used with
+ * lookup-array associativity.
+ */
+ if (lookup_array_assoc)
+ index = primary_domain_index - 1;
+ else {
+ index = primary_domain_index;
+ max_array_index = of_read_number(associativity, 1);
+ }
+ if (index > max_array_index)
+ goto out;
- if (of_read_number(associativity, 1) >= primary_domain_index)
- nid = of_read_number(&associativity[primary_domain_index], 1);
-
+ nid = of_read_number(&associativity[index], 1);
/* POWER4 LPAR uses 0xffff as invalid node */
if (nid == 0xffff || nid >= nr_node_ids)
nid = NUMA_NO_NODE;
@@ -192,6 +203,15 @@ static int associativity_to_nid(const __be32 *associativity)
return nid;
}
+/*
+ * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
+ * info is found.
+ */
+static inline int associativity_to_nid(const __be32 *associativity)
+{
+ return __associativity_to_nid(associativity, false, 0);
+}
+
static int __cpu_form2_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
{
int dist;
@@ -295,19 +315,38 @@ int of_node_to_nid(struct device_node *device)
}
EXPORT_SYMBOL(of_node_to_nid);
-static void __initialize_form1_numa_distance(const __be32 *associativity)
+static void __initialize_form1_numa_distance(const __be32 *associativity,
+ bool lookup_array_assoc,
+ int max_array_index)
{
int i, nid;
+ int index_offset = 0;
if (affinity_form != FORM1_AFFINITY)
return;
+ /*
+ * ibm,associativity-lookup-array doesn't have element
+ * count at the start of the associativity. Hence
+ * decrement the distance_ref_points index when used with
+ * lookup-array associativity.
+ */
+ if (lookup_array_assoc)
+ index_offset = 1;
+ else
+ max_array_index = of_read_number(associativity, 1);
- nid = associativity_to_nid(associativity);
+ nid = __associativity_to_nid(associativity, lookup_array_assoc, max_array_index);
if (nid != NUMA_NO_NODE) {
for (i = 0; i < distance_ref_points_depth; i++) {
const __be32 *entry;
+ int index = be32_to_cpu(distance_ref_points[i]) - index_offset;
- entry = &associativity[be32_to_cpu(distance_ref_points[i])];
+ /*
+ * broken hierarchy, return with broken distance table
+ */
+ if (index > max_array_index)
+ return;
+ entry = &associativity[index];
distance_lookup_table[nid][i] = of_read_number(entry, 1);
}
}
@@ -321,7 +360,7 @@ static void initialize_form1_numa_distance(struct device_node *node)
if (!associativity)
return;
- __initialize_form1_numa_distance(associativity);
+ __initialize_form1_numa_distance(associativity, false, 0);
}
/*
@@ -586,27 +625,14 @@ static int get_nid_and_numa_distance(struct drmem_lmb *lmb)
if (primary_domain_index <= aa.array_sz &&
!(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
- index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
- nid = of_read_number(&aa.arrays[index], 1);
+ const __be32 *associativity;
- if (nid == 0xffff || nid >= nr_node_ids)
- nid = default_nid;
+ index = lmb->aa_index * aa.array_sz;
+ associativity = &aa.arrays[index];
+ nid = __associativity_to_nid(associativity, true, aa.array_sz - 1);
if (nid > 0 && affinity_form == FORM1_AFFINITY) {
- int i;
- const __be32 *associativity;
-
- index = lmb->aa_index * aa.array_sz;
- associativity = &aa.arrays[index];
- /*
- * lookup array associativity entries have different format
- * There is no length of the array as the first element.
- */
- for (i = 0; i < distance_ref_points_depth; i++) {
- const __be32 *entry;
-
- entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
- distance_lookup_table[nid][i] = of_read_number(entry, 1);
- }
+ __initialize_form1_numa_distance(associativity,
+ true, aa.array_sz - 1);
}
}
return nid;
@@ -632,9 +658,11 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
if (primary_domain_index <= aa.array_sz &&
!(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
- index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
- nid = of_read_number(&aa.arrays[index], 1);
+ const __be32 *associativity;
+ index = lmb->aa_index * aa.array_sz;
+ associativity = &aa.arrays[index];
+ nid = __associativity_to_nid(associativity, true, aa.array_sz - 1);
if (nid == 0xffff || nid >= nr_node_ids)
nid = default_nid;
}
@@ -939,7 +967,7 @@ static int __init parse_numa_properties(void)
if (__vphn_get_associativity(i, vphn_assoc) == 0) {
nid = associativity_to_nid(vphn_assoc);
- __initialize_form1_numa_distance(vphn_assoc);
+ __initialize_form1_numa_distance(vphn_assoc, false, 0);
} else {
/*
@@ -953,7 +981,7 @@ static int __init parse_numa_properties(void)
associativity = of_get_associativity(cpu);
if (associativity) {
nid = associativity_to_nid(associativity);
- __initialize_form1_numa_distance(associativity);
+ __initialize_form1_numa_distance(associativity, false, 0);
}
of_node_put(cpu);
}
@@ -993,7 +1021,7 @@ static int __init parse_numa_properties(void)
associativity = of_get_associativity(memory);
if (associativity) {
nid = associativity_to_nid(associativity);
- __initialize_form1_numa_distance(associativity);
+ __initialize_form1_numa_distance(associativity, false, 0);
} else
nid = default_nid;
^ permalink raw reply
* [PATCH] tests/nvdimm/ndtest: Simulate nvdimm health, DSC and smart-inject
From: Shivaprasad G Bhat @ 2021-07-27 5:50 UTC (permalink / raw)
To: nvdimm, ellerman
Cc: santosh, sbhat, aneesh.kumar, vaibhav, dan.j.williams,
linuxppc-dev, ira.weiny
The 'papr_scm' module and 'papr' implementation in libndctl supports
PDSMs for reporting PAPR NVDIMM health, its dirty-shutdown-count and
injecting smart-error. This patch adds support for those PDSMs in
ndtest module so that PDSM specific paths in libndctl can be exercised.
Signed-off-by: Shivaprasad G Bhat <sbhat@linux.ibm.com>
---
The patch depends on the PAPR PDSM smart-inject payload definitions
added with the patch - https://www.mail-archive.com/linuxppc-dev@lists.ozlabs.org/msg191337.html
tools/testing/nvdimm/test/ndtest.c | 149 ++++++++++++++++++++++++++++++++++++
tools/testing/nvdimm/test/ndtest.h | 7 ++
2 files changed, 156 insertions(+)
diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c
index 00ec2c213061..6622e8adbd11 100644
--- a/tools/testing/nvdimm/test/ndtest.c
+++ b/tools/testing/nvdimm/test/ndtest.c
@@ -14,6 +14,7 @@
#include <linux/printk.h>
#include <linux/seq_buf.h>
#include <linux/papr_scm.h>
+#include <uapi/linux/papr_pdsm.h>
#include "../watermark.h"
#include "nfit_test.h"
@@ -49,6 +50,10 @@ static struct ndtest_dimm dimm_group1[] = {
.uuid_str = "1e5c75d2-b618-11ea-9aa3-507b9ddc0f72",
.physical_id = 0,
.num_formats = 2,
+ .flags = PAPR_PMEM_HEALTH_NON_CRITICAL,
+ .extension_flags = PDSM_DIMM_DSC_VALID | PDSM_DIMM_HEALTH_RUN_GAUGE_VALID,
+ .dimm_fuel_gauge = 95,
+ .dimm_dsc = 42,
},
{
.size = DIMM_SIZE,
@@ -56,6 +61,10 @@ static struct ndtest_dimm dimm_group1[] = {
.uuid_str = "1c4d43ac-b618-11ea-be80-507b9ddc0f72",
.physical_id = 1,
.num_formats = 2,
+ .flags = PAPR_PMEM_HEALTH_NON_CRITICAL,
+ .extension_flags = PDSM_DIMM_DSC_VALID | PDSM_DIMM_HEALTH_RUN_GAUGE_VALID,
+ .dimm_fuel_gauge = 95,
+ .dimm_dsc = 42,
},
{
.size = DIMM_SIZE,
@@ -63,6 +72,10 @@ static struct ndtest_dimm dimm_group1[] = {
.uuid_str = "a9f17ffc-b618-11ea-b36d-507b9ddc0f72",
.physical_id = 2,
.num_formats = 2,
+ .flags = PAPR_PMEM_HEALTH_NON_CRITICAL,
+ .extension_flags = PDSM_DIMM_DSC_VALID | PDSM_DIMM_HEALTH_RUN_GAUGE_VALID,
+ .dimm_fuel_gauge = 95,
+ .dimm_dsc = 42,
},
{
.size = DIMM_SIZE,
@@ -70,6 +83,10 @@ static struct ndtest_dimm dimm_group1[] = {
.uuid_str = "b6b83b22-b618-11ea-8aae-507b9ddc0f72",
.physical_id = 3,
.num_formats = 2,
+ .flags = PAPR_PMEM_HEALTH_NON_CRITICAL,
+ .extension_flags = PDSM_DIMM_DSC_VALID | PDSM_DIMM_HEALTH_RUN_GAUGE_VALID,
+ .dimm_fuel_gauge = 95,
+ .dimm_dsc = 42,
},
{
.size = DIMM_SIZE,
@@ -297,6 +314,103 @@ static int ndtest_get_config_size(struct ndtest_dimm *dimm, unsigned int buf_len
return 0;
}
+static int ndtest_pdsm_health(struct ndtest_dimm *dimm,
+ union nd_pdsm_payload *payload,
+ unsigned int buf_len)
+{
+ struct nd_papr_pdsm_health *health = &payload->health;
+
+ if (buf_len < sizeof(health))
+ return -EINVAL;
+
+ health->extension_flags = 0;
+ health->dimm_unarmed = !!(dimm->flags & PAPR_PMEM_UNARMED_MASK);
+ health->dimm_bad_shutdown = !!(dimm->flags & PAPR_PMEM_BAD_SHUTDOWN_MASK);
+ health->dimm_bad_restore = !!(dimm->flags & PAPR_PMEM_BAD_RESTORE_MASK);
+ health->dimm_health = PAPR_PDSM_DIMM_HEALTHY;
+
+ if (dimm->flags & PAPR_PMEM_HEALTH_FATAL)
+ health->dimm_health = PAPR_PDSM_DIMM_FATAL;
+ else if (dimm->flags & PAPR_PMEM_HEALTH_CRITICAL)
+ health->dimm_health = PAPR_PDSM_DIMM_CRITICAL;
+ else if (dimm->flags & PAPR_PMEM_HEALTH_UNHEALTHY ||
+ dimm->flags & PAPR_PMEM_HEALTH_NON_CRITICAL)
+ health->dimm_health = PAPR_PDSM_DIMM_UNHEALTHY;
+
+ health->extension_flags = 0;
+ if (dimm->extension_flags & PDSM_DIMM_HEALTH_RUN_GAUGE_VALID) {
+ health->dimm_fuel_gauge = dimm->dimm_fuel_gauge;
+ health->extension_flags |= PDSM_DIMM_HEALTH_RUN_GAUGE_VALID;
+ }
+ if (dimm->extension_flags & PDSM_DIMM_DSC_VALID) {
+ health->dimm_dsc = dimm->dimm_dsc;
+ health->extension_flags |= PDSM_DIMM_DSC_VALID;
+ }
+
+ return 0;
+}
+
+static void smart_notify(struct ndtest_dimm *dimm)
+{
+ struct device *bus = dimm->dev->parent;
+
+ if (!(dimm->flags & PAPR_PMEM_HEALTH_NON_CRITICAL) ||
+ (dimm->flags & PAPR_PMEM_BAD_SHUTDOWN_MASK)) {
+ device_lock(bus);
+ /* send smart notification */
+ if (dimm->notify_handle)
+ sysfs_notify_dirent(dimm->notify_handle);
+ device_unlock(bus);
+ }
+}
+
+static int ndtest_pdsm_smart_inject(struct ndtest_dimm *dimm,
+ union nd_pdsm_payload *payload,
+ unsigned int buf_len)
+{
+ struct nd_papr_pdsm_smart_inject *inj = &payload->smart_inject;
+
+ if (buf_len < sizeof(inj))
+ return -EINVAL;
+
+ if (inj->flags & PDSM_SMART_INJECT_HEALTH_FATAL) {
+ if (inj->fatal_enable)
+ dimm->flags |= PAPR_PMEM_HEALTH_FATAL;
+ else
+ dimm->flags &= ~PAPR_PMEM_HEALTH_FATAL;
+ }
+ if (inj->flags & PDSM_SMART_INJECT_BAD_SHUTDOWN) {
+ if (inj->unsafe_shutdown_enable)
+ dimm->flags |= PAPR_PMEM_SHUTDOWN_DIRTY;
+ else
+ dimm->flags &= ~PAPR_PMEM_SHUTDOWN_DIRTY;
+ }
+ smart_notify(dimm);
+
+ return 0;
+}
+
+static int ndtest_dimm_cmd_call(struct ndtest_dimm *dimm, unsigned int buf_len,
+ void *buf)
+{
+ struct nd_cmd_pkg *call_pkg = buf;
+ unsigned int len = call_pkg->nd_size_in + call_pkg->nd_size_out;
+ struct nd_pkg_pdsm *pdsm = (struct nd_pkg_pdsm *) call_pkg->nd_payload;
+ union nd_pdsm_payload *payload = &(pdsm->payload);
+ unsigned int func = call_pkg->nd_command;
+
+ switch (func) {
+ case PAPR_PDSM_HEALTH:
+ return ndtest_pdsm_health(dimm, payload, len);
+ case PAPR_PDSM_SMART_INJECT:
+ return ndtest_pdsm_smart_inject(dimm, payload, len);
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int ndtest_ctl(struct nvdimm_bus_descriptor *nd_desc,
struct nvdimm *nvdimm, unsigned int cmd, void *buf,
unsigned int buf_len, int *cmd_rc)
@@ -326,6 +440,9 @@ static int ndtest_ctl(struct nvdimm_bus_descriptor *nd_desc,
case ND_CMD_SET_CONFIG_DATA:
*cmd_rc = ndtest_config_set(dimm, buf_len, buf);
break;
+ case ND_CMD_CALL:
+ *cmd_rc = ndtest_dimm_cmd_call(dimm, buf_len, buf);
+ break;
default:
return -EINVAL;
}
@@ -615,6 +732,8 @@ static void put_dimms(void *data)
for (i = 0; i < p->config->dimm_count; i++)
if (p->config->dimms[i].dev) {
+ if (p->config->dimms[i].notify_handle)
+ sysfs_put(p->config->dimms[i].notify_handle);
device_unregister(p->config->dimms[i].dev);
p->config->dimms[i].dev = NULL;
}
@@ -827,6 +946,18 @@ static ssize_t flags_show(struct device *dev,
}
static DEVICE_ATTR_RO(flags);
+#define PAPR_PMEM_DIMM_CMD_MASK \
+ ((1U << PAPR_PDSM_HEALTH) \
+ | (1U << PAPR_PDSM_SMART_INJECT))
+
+static ssize_t dsm_mask_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%#x\n", PAPR_PMEM_DIMM_CMD_MASK);
+}
+
+static DEVICE_ATTR_RO(dsm_mask);
+
static struct attribute *ndtest_nvdimm_attributes[] = {
&dev_attr_nvdimm_show_handle.attr,
&dev_attr_vendor.attr,
@@ -838,6 +969,7 @@ static struct attribute *ndtest_nvdimm_attributes[] = {
&dev_attr_format.attr,
&dev_attr_format1.attr,
&dev_attr_flags.attr,
+ &dev_attr_dsm_mask.attr,
NULL,
};
@@ -857,6 +989,7 @@ static int ndtest_dimm_register(struct ndtest_priv *priv,
{
struct device *dev = &priv->pdev.dev;
unsigned long dimm_flags = dimm->flags;
+ struct kernfs_node *papr_kernfs;
if (dimm->num_formats > 1) {
set_bit(NDD_ALIASING, &dimm_flags);
@@ -883,6 +1016,20 @@ static int ndtest_dimm_register(struct ndtest_priv *priv,
return -ENOMEM;
}
+ nd_synchronize();
+
+ papr_kernfs = sysfs_get_dirent(nvdimm_kobj(dimm->nvdimm)->sd, "papr");
+ if (!papr_kernfs) {
+ pr_err("Could not initialize the notifier handle\n");
+ return 0;
+ }
+
+ dimm->notify_handle = sysfs_get_dirent(papr_kernfs, "flags");
+ sysfs_put(papr_kernfs);
+ if (!dimm->notify_handle) {
+ pr_err("Could not initialize the notifier handle\n");
+ return 0;
+ }
return 0;
}
@@ -954,6 +1101,8 @@ static int ndtest_bus_register(struct ndtest_priv *p)
p->bus_desc.provider_name = NULL;
p->bus_desc.attr_groups = ndtest_attribute_groups;
+ set_bit(NVDIMM_FAMILY_PAPR, &p->bus_desc.dimm_family_mask);
+
p->bus = nvdimm_bus_register(&p->pdev.dev, &p->bus_desc);
if (!p->bus) {
dev_err(&p->pdev.dev, "Error creating nvdimm bus %pOF\n", p->dn);
diff --git a/tools/testing/nvdimm/test/ndtest.h b/tools/testing/nvdimm/test/ndtest.h
index 8f27ad6f7319..e18b3b006fa2 100644
--- a/tools/testing/nvdimm/test/ndtest.h
+++ b/tools/testing/nvdimm/test/ndtest.h
@@ -49,6 +49,13 @@ struct ndtest_dimm {
int id;
int fail_cmd_code;
u8 no_alias;
+
+ struct kernfs_node *notify_handle;
+
+ /* SMART Health information */
+ u32 extension_flags;
+ u16 dimm_fuel_gauge;
+ u64 dimm_dsc;
};
struct ndtest_mapping {
^ permalink raw reply related
* Re: [PATCH v5 4/6] powerpc/pseries: Consolidate different NUMA distance update code paths
From: David Gibson @ 2021-07-27 5:59 UTC (permalink / raw)
To: Aneesh Kumar K.V; +Cc: Nathan Lynch, Daniel Henrique Barboza, linuxppc-dev
In-Reply-To: <87r1fktory.fsf@linux.ibm.com>
[-- Attachment #1: Type: text/plain, Size: 10105 bytes --]
On Tue, Jul 27, 2021 at 09:02:33AM +0530, Aneesh Kumar K.V wrote:
> David Gibson <david@gibson.dropbear.id.au> writes:
>
> > On Thu, Jul 22, 2021 at 12:37:46PM +0530, Aneesh Kumar K.V wrote:
> >> David Gibson <david@gibson.dropbear.id.au> writes:
> >>
> >> > On Mon, Jun 28, 2021 at 08:41:15PM +0530, Aneesh Kumar K.V wrote:
>
> ....
>
> >
> >> >
> >> >> + nid = of_read_number(&aa.arrays[index], 1);
> >> >> +
> >> >> + if (nid == 0xffff || nid >= nr_node_ids)
> >> >> + nid = default_nid;
> >> >> + if (nid > 0 && affinity_form == FORM1_AFFINITY) {
> >> >> + int i;
> >> >> + const __be32 *associativity;
> >> >> +
> >> >> + index = lmb->aa_index * aa.array_sz;
> >> >> + associativity = &aa.arrays[index];
> >> >> + /*
> >> >> + * lookup array associativity entries have different format
> >> >> + * There is no length of the array as the first element.
> >> >
> >> > The difference it very small, and this is not a hot path. Couldn't
> >> > you reduce a chunk of code by prepending aa.array_sz, then re-using
> >> > __initialize_form1_numa_distance. Or even making
> >> > __initialize_form1_numa_distance() take the length as a parameter.
> >>
> >> The changes are small but confusing w.r.t how we look at the
> >> associativity-lookup-arrays. The way we interpret associativity array
> >> and associativity lookup array using primary_domain_index is different.
> >> Hence the '-1' in the node lookup here.
> >
> > They're really not, though. It's exactly the same interpretation of
> > the associativity array itself - it's just that one of them has the
> > array prepended with a (redundant) length. So you can make
> > __initialize_form1_numa_distance() work on the "bare" associativity
> > array, with a given length. Here you call it with aa.array_sz as the
> > length, and in the other place you call it with prop[0] as the length.
> >
> >>
> >> index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
> >> nid = of_read_number(&aa.arrays[index], 1);
> >>
> >>
> >> >
> >> >> + */
> >> >> + for (i = 0; i < max_associativity_domain_index; i++) {
> >> >> + const __be32 *entry;
> >> >> +
> >> >> + entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
> >> >
> >> > Does anywhere verify that distance_ref_points[i] <= aa.array_size for
> >> > every i?
> >>
> >> We do check for
> >>
> >> if (primary_domain_index <= aa.array_sz &&
> >
> > Right, but that doesn't check the other distance_ref_points entries.
> > Not that there's any reason to have extra entries with Form2, but we
> > still don't want stray array accesses.
>
> This is how the change looks. I am not convinced this makes it simpler.
It's not, but that's because the lookup_array_assoc flag is not needed...
> I will add that as the last patch and we can drop that if we find that
> not helpful?
>
> modified arch/powerpc/mm/numa.c
> @@ -171,20 +171,31 @@ static void unmap_cpu_from_node(unsigned long cpu)
> }
> #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
>
> -/*
> - * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
> - * info is found.
> - */
> -static int associativity_to_nid(const __be32 *associativity)
> +static int __associativity_to_nid(const __be32 *associativity,
> + bool lookup_array_assoc,
> + int max_array_index)
> {
> int nid = NUMA_NO_NODE;
> + int index;
>
> if (!numa_enabled)
> goto out;
> + /*
> + * ibm,associativity-lookup-array doesn't have element
> + * count at the start of the associativity. Hence
> + * decrement the primary_domain_index when used with
> + * lookup-array associativity.
> + */
> + if (lookup_array_assoc)
> + index = primary_domain_index - 1;
> + else {
> + index = primary_domain_index;
> + max_array_index = of_read_number(associativity, 1);
> + }
> + if (index > max_array_index)
> + goto out;
So, the associativity-array-with-length is exactly a length, followed
by an associativity-array-without-length. What I was suggesting is
you make this function only take an
associativity-array-without-length, with the length passed separately.
Where you want to use it on an associativity-array-with-length, stored
in __be32 *awl, you just invoke it as:
associativity_to_nid(awl + 1, of_read_number(awl, 1));
> - if (of_read_number(associativity, 1) >= primary_domain_index)
> - nid = of_read_number(&associativity[primary_domain_index], 1);
> -
> + nid = of_read_number(&associativity[index], 1);
> /* POWER4 LPAR uses 0xffff as invalid node */
> if (nid == 0xffff || nid >= nr_node_ids)
> nid = NUMA_NO_NODE;
> @@ -192,6 +203,15 @@ static int associativity_to_nid(const __be32 *associativity)
> return nid;
> }
>
> +/*
> + * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
> + * info is found.
> + */
> +static inline int associativity_to_nid(const __be32 *associativity)
> +{
> + return __associativity_to_nid(associativity, false, 0);
> +}
> +
> static int __cpu_form2_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
> {
> int dist;
> @@ -295,19 +315,38 @@ int of_node_to_nid(struct device_node *device)
> }
> EXPORT_SYMBOL(of_node_to_nid);
>
> -static void __initialize_form1_numa_distance(const __be32 *associativity)
> +static void __initialize_form1_numa_distance(const __be32 *associativity,
> + bool lookup_array_assoc,
> + int max_array_index)
> {
> int i, nid;
> + int index_offset = 0;
>
> if (affinity_form != FORM1_AFFINITY)
> return;
> + /*
> + * ibm,associativity-lookup-array doesn't have element
> + * count at the start of the associativity. Hence
> + * decrement the distance_ref_points index when used with
> + * lookup-array associativity.
> + */
> + if (lookup_array_assoc)
> + index_offset = 1;
> + else
> + max_array_index = of_read_number(associativity, 1);
>
> - nid = associativity_to_nid(associativity);
> + nid = __associativity_to_nid(associativity, lookup_array_assoc, max_array_index);
> if (nid != NUMA_NO_NODE) {
> for (i = 0; i < distance_ref_points_depth; i++) {
> const __be32 *entry;
> + int index = be32_to_cpu(distance_ref_points[i]) - index_offset;
>
> - entry = &associativity[be32_to_cpu(distance_ref_points[i])];
> + /*
> + * broken hierarchy, return with broken distance table
> + */
> + if (index > max_array_index)
> + return;
> + entry = &associativity[index];
> distance_lookup_table[nid][i] = of_read_number(entry, 1);
> }
> }
> @@ -321,7 +360,7 @@ static void initialize_form1_numa_distance(struct device_node *node)
> if (!associativity)
> return;
>
> - __initialize_form1_numa_distance(associativity);
> + __initialize_form1_numa_distance(associativity, false, 0);
> }
>
> /*
> @@ -586,27 +625,14 @@ static int get_nid_and_numa_distance(struct drmem_lmb *lmb)
>
> if (primary_domain_index <= aa.array_sz &&
> !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
> - index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
> - nid = of_read_number(&aa.arrays[index], 1);
> + const __be32 *associativity;
>
> - if (nid == 0xffff || nid >= nr_node_ids)
> - nid = default_nid;
> + index = lmb->aa_index * aa.array_sz;
> + associativity = &aa.arrays[index];
> + nid = __associativity_to_nid(associativity, true, aa.array_sz - 1);
> if (nid > 0 && affinity_form == FORM1_AFFINITY) {
> - int i;
> - const __be32 *associativity;
> -
> - index = lmb->aa_index * aa.array_sz;
> - associativity = &aa.arrays[index];
> - /*
> - * lookup array associativity entries have different format
> - * There is no length of the array as the first element.
> - */
> - for (i = 0; i < distance_ref_points_depth; i++) {
> - const __be32 *entry;
> -
> - entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
> - distance_lookup_table[nid][i] = of_read_number(entry, 1);
> - }
> + __initialize_form1_numa_distance(associativity,
> + true, aa.array_sz - 1);
> }
> }
> return nid;
> @@ -632,9 +658,11 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
>
> if (primary_domain_index <= aa.array_sz &&
> !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
> - index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
> - nid = of_read_number(&aa.arrays[index], 1);
> + const __be32 *associativity;
>
> + index = lmb->aa_index * aa.array_sz;
> + associativity = &aa.arrays[index];
> + nid = __associativity_to_nid(associativity, true, aa.array_sz - 1);
> if (nid == 0xffff || nid >= nr_node_ids)
> nid = default_nid;
> }
> @@ -939,7 +967,7 @@ static int __init parse_numa_properties(void)
>
> if (__vphn_get_associativity(i, vphn_assoc) == 0) {
> nid = associativity_to_nid(vphn_assoc);
> - __initialize_form1_numa_distance(vphn_assoc);
> + __initialize_form1_numa_distance(vphn_assoc, false, 0);
> } else {
>
> /*
> @@ -953,7 +981,7 @@ static int __init parse_numa_properties(void)
> associativity = of_get_associativity(cpu);
> if (associativity) {
> nid = associativity_to_nid(associativity);
> - __initialize_form1_numa_distance(associativity);
> + __initialize_form1_numa_distance(associativity, false, 0);
> }
> of_node_put(cpu);
> }
> @@ -993,7 +1021,7 @@ static int __init parse_numa_properties(void)
> associativity = of_get_associativity(memory);
> if (associativity) {
> nid = associativity_to_nid(associativity);
> - __initialize_form1_numa_distance(associativity);
> + __initialize_form1_numa_distance(associativity, false, 0);
> } else
> nid = default_nid;
>
>
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* switch the block layer to use kmap_local_page v3
From: Christoph Hellwig @ 2021-07-27 5:56 UTC (permalink / raw)
To: Jens Axboe, Thomas Gleixner
Cc: linux-arch, linux-block, Thomas Bogendoerfer, Mike Snitzer,
Geoff Levand, linuxppc-dev, ceph-devel, linux-mips,
Dongsheng Yang, linux-kernel, James E.J. Bottomley, dm-devel,
Andrew Morton, Ira Weiny, Ilya Dryomov
Hi all,
this series switches the core block layer code and all users of the
existing bvec kmap helpers to use kmap_local_page. Drivers that
currently use open coded kmap_atomic calls will converted in a follow
on series.
To do so a new kunmap variant is added that calls
flush_kernel_dcache_page. I'm not entirely sure where to call
flush_dcache_page vs flush_kernel_dcache_page, so I've tried to follow
the documentation here, but additional feedback would be welcome.
Note that the ps3disk has a minir conflict with the
flush_kernel_dcache_page removal in linux-next through the -mm tree.
I had hoped that change would go into 5.14, but it seems like it is
being held for 5.15.
Changes since v2:
- rely on the flush_dcache_helpers in memcpy_to_page and memzero_page
that now hit mainline
Changes since v1:
- add more/better comments
- add a new kunmap_local_dirty helper to feal with
flush(_kernel)_dcache_page
Diffstat:
arch/mips/include/asm/mach-rc32434/rb.h | 2 -
block/bio-integrity.c | 14 +++-----
block/bio.c | 37 ++++++----------------
block/blk-map.c | 2 -
block/bounce.c | 39 +++++-------------------
block/t10-pi.c | 16 +++------
drivers/block/ps3disk.c | 19 +----------
drivers/block/rbd.c | 15 +--------
drivers/md/dm-writecache.c | 5 +--
include/linux/bio.h | 42 -------------------------
include/linux/bvec.h | 52 ++++++++++++++++++++++++++++++--
include/linux/highmem-internal.h | 7 ++++
include/linux/highmem.h | 10 ++++--
13 files changed, 102 insertions(+), 158 deletions(-)
^ permalink raw reply
* [PATCH 01/15] MIPS: don't include <linux/genhd.h> in <asm/mach-rc32434/rb.h>
From: Christoph Hellwig @ 2021-07-27 5:56 UTC (permalink / raw)
To: Jens Axboe, Thomas Gleixner
Cc: linux-arch, linux-block, Thomas Bogendoerfer, Chaitanya Kulkarni,
Mike Snitzer, Geoff Levand, linuxppc-dev, ceph-devel, linux-mips,
Dongsheng Yang, linux-kernel, James E.J. Bottomley, dm-devel,
Martin K . Petersen, Andrew Morton, Ira Weiny, Ilya Dryomov
In-Reply-To: <20210727055646.118787-1-hch@lst.de>
There is no need to include genhd.h from a random arch header, and not
doing so prevents the possibility for nasty include loops.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
---
arch/mips/include/asm/mach-rc32434/rb.h | 2 --
1 file changed, 2 deletions(-)
diff --git a/arch/mips/include/asm/mach-rc32434/rb.h b/arch/mips/include/asm/mach-rc32434/rb.h
index d502673a4f6c..34d179ca020b 100644
--- a/arch/mips/include/asm/mach-rc32434/rb.h
+++ b/arch/mips/include/asm/mach-rc32434/rb.h
@@ -7,8 +7,6 @@
#ifndef __ASM_RC32434_RB_H
#define __ASM_RC32434_RB_H
-#include <linux/genhd.h>
-
#define REGBASE 0x18000000
#define IDT434_REG_BASE ((volatile void *) KSEG1ADDR(REGBASE))
#define UART0BASE 0x58000
--
2.30.2
^ permalink raw reply related
* [PATCH 02/15] bvec: fix the include guards for bvec.h
From: Christoph Hellwig @ 2021-07-27 5:56 UTC (permalink / raw)
To: Jens Axboe, Thomas Gleixner
Cc: linux-arch, linux-block, Thomas Bogendoerfer, Bart Van Assche,
Mike Snitzer, Geoff Levand, linuxppc-dev, Chaitanya Kulkarni,
ceph-devel, linux-mips, Dongsheng Yang, linux-kernel,
James E.J. Bottomley, dm-devel, Martin K . Petersen,
Andrew Morton, Ira Weiny, Ilya Dryomov
In-Reply-To: <20210727055646.118787-1-hch@lst.de>
Fix the include guards to match the file naming.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
---
include/linux/bvec.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index ff832e698efb..883faf5f1523 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -4,8 +4,8 @@
*
* Copyright (C) 2001 Ming Lei <ming.lei@canonical.com>
*/
-#ifndef __LINUX_BVEC_ITER_H
-#define __LINUX_BVEC_ITER_H
+#ifndef __LINUX_BVEC_H
+#define __LINUX_BVEC_H
#include <linux/bug.h>
#include <linux/errno.h>
@@ -183,4 +183,4 @@ static inline void bvec_advance(const struct bio_vec *bvec,
}
}
-#endif /* __LINUX_BVEC_ITER_H */
+#endif /* __LINUX_BVEC_H */
--
2.30.2
^ permalink raw reply related
* [PATCH 03/15] bvec: add a bvec_kmap_local helper
From: Christoph Hellwig @ 2021-07-27 5:56 UTC (permalink / raw)
To: Jens Axboe, Thomas Gleixner
Cc: linux-arch, linux-block, Thomas Bogendoerfer, Chaitanya Kulkarni,
Mike Snitzer, Geoff Levand, linuxppc-dev, ceph-devel, linux-mips,
Dongsheng Yang, linux-kernel, James E.J. Bottomley, dm-devel,
Martin K . Petersen, Andrew Morton, Ira Weiny, Ilya Dryomov
In-Reply-To: <20210727055646.118787-1-hch@lst.de>
Add a helper to call kmap_local_page on a bvec. There is no need for
an unmap helper given that kunmap_local accept any address in the mapped
page.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
---
include/linux/bvec.h | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 883faf5f1523..f8710af18eef 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -7,6 +7,7 @@
#ifndef __LINUX_BVEC_H
#define __LINUX_BVEC_H
+#include <linux/highmem.h>
#include <linux/bug.h>
#include <linux/errno.h>
#include <linux/limits.h>
@@ -183,4 +184,16 @@ static inline void bvec_advance(const struct bio_vec *bvec,
}
}
+/**
+ * bvec_kmap_local - map a bvec into the kernel virtual address space
+ * @bvec: bvec to map
+ *
+ * Must be called on single-page bvecs only. Call kunmap_local on the returned
+ * address to unmap.
+ */
+static inline void *bvec_kmap_local(struct bio_vec *bvec)
+{
+ return kmap_local_page(bvec->bv_page) + bvec->bv_offset;
+}
+
#endif /* __LINUX_BVEC_H */
--
2.30.2
^ permalink raw reply related
* [PATCH 04/15] bvec: add memcpy_{from, to}_bvec and memzero_bvec helper
From: Christoph Hellwig @ 2021-07-27 5:56 UTC (permalink / raw)
To: Jens Axboe, Thomas Gleixner
Cc: linux-arch, linux-block, Thomas Bogendoerfer, Chaitanya Kulkarni,
Mike Snitzer, Geoff Levand, linuxppc-dev, ceph-devel, linux-mips,
Dongsheng Yang, linux-kernel, James E.J. Bottomley, dm-devel,
Martin K . Petersen, Andrew Morton, Ira Weiny, Ilya Dryomov
In-Reply-To: <20210727055646.118787-1-hch@lst.de>
Add helpers to perform common memory operation on a bvec.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
---
include/linux/bvec.h | 33 +++++++++++++++++++++++++++++++++
1 file changed, 33 insertions(+)
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index f8710af18eef..f9fa43b940ff 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -196,4 +196,37 @@ static inline void *bvec_kmap_local(struct bio_vec *bvec)
return kmap_local_page(bvec->bv_page) + bvec->bv_offset;
}
+/**
+ * memcpy_from_bvec - copy data from a bvec
+ * @bvec: bvec to copy from
+ *
+ * Must be called on single-page bvecs only.
+ */
+static inline void memcpy_from_bvec(char *to, struct bio_vec *bvec)
+{
+ memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, bvec->bv_len);
+}
+
+/**
+ * memcpy_to_bvec - copy data to a bvec
+ * @bvec: bvec to copy to
+ *
+ * Must be called on single-page bvecs only.
+ */
+static inline void memcpy_to_bvec(struct bio_vec *bvec, const char *from)
+{
+ memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, bvec->bv_len);
+}
+
+/**
+ * memzero_bvec - zero all data in a bvec
+ * @bvec: bvec to zero
+ *
+ * Must be called on single-page bvecs only.
+ */
+static inline void memzero_bvec(struct bio_vec *bvec)
+{
+ memzero_page(bvec->bv_page, bvec->bv_offset, bvec->bv_len);
+}
+
#endif /* __LINUX_BVEC_H */
--
2.30.2
^ permalink raw reply related
* [PATCH 05/15] block: use memzero_page in zero_fill_bio
From: Christoph Hellwig @ 2021-07-27 5:56 UTC (permalink / raw)
To: Jens Axboe, Thomas Gleixner
Cc: linux-arch, linux-block, Thomas Bogendoerfer, Chaitanya Kulkarni,
Mike Snitzer, Geoff Levand, linuxppc-dev, ceph-devel, linux-mips,
Dongsheng Yang, linux-kernel, James E.J. Bottomley, dm-devel,
Martin K . Petersen, Andrew Morton, Ira Weiny, Ilya Dryomov
In-Reply-To: <20210727055646.118787-1-hch@lst.de>
Use memzero_bvec to zero each segment in the bio instead of manually
mapping and zeroing the data.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
---
block/bio.c | 9 ++-------
1 file changed, 2 insertions(+), 7 deletions(-)
diff --git a/block/bio.c b/block/bio.c
index 1fab762e079b..2e436bccb1e2 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -495,16 +495,11 @@ EXPORT_SYMBOL(bio_kmalloc);
void zero_fill_bio(struct bio *bio)
{
- unsigned long flags;
struct bio_vec bv;
struct bvec_iter iter;
- bio_for_each_segment(bv, bio, iter) {
- char *data = bvec_kmap_irq(&bv, &flags);
- memset(data, 0, bv.bv_len);
- flush_dcache_page(bv.bv_page);
- bvec_kunmap_irq(data, &flags);
- }
+ bio_for_each_segment(bv, bio, iter)
+ memzero_bvec(&bv);
}
EXPORT_SYMBOL(zero_fill_bio);
--
2.30.2
^ permalink raw reply related
* [PATCH 06/15] rbd: use memzero_bvec
From: Christoph Hellwig @ 2021-07-27 5:56 UTC (permalink / raw)
To: Jens Axboe, Thomas Gleixner
Cc: linux-arch, linux-block, Thomas Bogendoerfer, Martin K . Petersen,
Mike Snitzer, Geoff Levand, linuxppc-dev, ceph-devel, linux-mips,
Dongsheng Yang, linux-kernel, James E.J. Bottomley, dm-devel,
Andrew Morton, Ira Weiny, Ilya Dryomov
In-Reply-To: <20210727055646.118787-1-hch@lst.de>
Use memzero_bvec instead of reimplementing it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
---
drivers/block/rbd.c | 15 ++-------------
1 file changed, 2 insertions(+), 13 deletions(-)
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 90b947c96402..6d596c2c2cd6 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1219,24 +1219,13 @@ static void rbd_dev_mapping_clear(struct rbd_device *rbd_dev)
rbd_dev->mapping.size = 0;
}
-static void zero_bvec(struct bio_vec *bv)
-{
- void *buf;
- unsigned long flags;
-
- buf = bvec_kmap_irq(bv, &flags);
- memset(buf, 0, bv->bv_len);
- flush_dcache_page(bv->bv_page);
- bvec_kunmap_irq(buf, &flags);
-}
-
static void zero_bios(struct ceph_bio_iter *bio_pos, u32 off, u32 bytes)
{
struct ceph_bio_iter it = *bio_pos;
ceph_bio_iter_advance(&it, off);
ceph_bio_iter_advance_step(&it, bytes, ({
- zero_bvec(&bv);
+ memzero_bvec(&bv);
}));
}
@@ -1246,7 +1235,7 @@ static void zero_bvecs(struct ceph_bvec_iter *bvec_pos, u32 off, u32 bytes)
ceph_bvec_iter_advance(&it, off);
ceph_bvec_iter_advance_step(&it, bytes, ({
- zero_bvec(&bv);
+ memzero_bvec(&bv);
}));
}
--
2.30.2
^ permalink raw reply related
* [PATCH 07/15] dm-writecache: use bvec_kmap_local instead of bvec_kmap_irq
From: Christoph Hellwig @ 2021-07-27 5:56 UTC (permalink / raw)
To: Jens Axboe, Thomas Gleixner
Cc: linux-arch, linux-block, Thomas Bogendoerfer, Martin K . Petersen,
Mike Snitzer, Geoff Levand, linuxppc-dev, ceph-devel, linux-mips,
Dongsheng Yang, linux-kernel, James E.J. Bottomley, dm-devel,
Andrew Morton, Ira Weiny, Ilya Dryomov
In-Reply-To: <20210727055646.118787-1-hch@lst.de>
There is no need to disable interrupts in bio_copy_block, and the local
only mappings helps to avoid any sort of problems with stray writes
into the bio data.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
---
drivers/md/dm-writecache.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index e21e29e81bbf..3d2cf811ec3e 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -1214,14 +1214,13 @@ static void memcpy_flushcache_optimized(void *dest, void *source, size_t size)
static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data)
{
void *buf;
- unsigned long flags;
unsigned size;
int rw = bio_data_dir(bio);
unsigned remaining_size = wc->block_size;
do {
struct bio_vec bv = bio_iter_iovec(bio, bio->bi_iter);
- buf = bvec_kmap_irq(&bv, &flags);
+ buf = bvec_kmap_local(&bv);
size = bv.bv_len;
if (unlikely(size > remaining_size))
size = remaining_size;
@@ -1239,7 +1238,7 @@ static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data
memcpy_flushcache_optimized(data, buf, size);
}
- bvec_kunmap_irq(buf, &flags);
+ kunmap_local(buf);
data = (char *)data + size;
remaining_size -= size;
--
2.30.2
^ permalink raw reply related
* [PATCH 08/15] ps3disk: use memcpy_{from,to}_bvec
From: Christoph Hellwig @ 2021-07-27 5:56 UTC (permalink / raw)
To: Jens Axboe, Thomas Gleixner
Cc: linux-arch, linux-block, Thomas Bogendoerfer, Martin K . Petersen,
Mike Snitzer, Geoff Levand, linuxppc-dev, ceph-devel, linux-mips,
Dongsheng Yang, linux-kernel, James E.J. Bottomley, dm-devel,
Andrew Morton, Ira Weiny, Ilya Dryomov
In-Reply-To: <20210727055646.118787-1-hch@lst.de>
Use the bvec helpers instead of open coding the copy.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Tested-by: Geoff Levand <geoff@infradead.org>
---
drivers/block/ps3disk.c | 18 ++----------------
1 file changed, 2 insertions(+), 16 deletions(-)
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index f374ea2c67ce..8d51efbe045d 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -83,26 +83,12 @@ static void ps3disk_scatter_gather(struct ps3_storage_device *dev,
unsigned int offset = 0;
struct req_iterator iter;
struct bio_vec bvec;
- unsigned int i = 0;
- size_t size;
- void *buf;
rq_for_each_segment(bvec, req, iter) {
- unsigned long flags;
- dev_dbg(&dev->sbd.core, "%s:%u: bio %u: %u sectors from %llu\n",
- __func__, __LINE__, i, bio_sectors(iter.bio),
- iter.bio->bi_iter.bi_sector);
-
- size = bvec.bv_len;
- buf = bvec_kmap_irq(&bvec, &flags);
if (gather)
- memcpy(dev->bounce_buf+offset, buf, size);
+ memcpy_from_bvec(dev->bounce_buf + offset, &bvec);
else
- memcpy(buf, dev->bounce_buf+offset, size);
- offset += size;
- flush_kernel_dcache_page(bvec.bv_page);
- bvec_kunmap_irq(buf, &flags);
- i++;
+ memcpy_to_bvec(&bvec, dev->bounce_buf + offset);
}
}
--
2.30.2
^ permalink raw reply related
* [PATCH 09/15] block: remove bvec_kmap_irq and bvec_kunmap_irq
From: Christoph Hellwig @ 2021-07-27 5:56 UTC (permalink / raw)
To: Jens Axboe, Thomas Gleixner
Cc: linux-arch, linux-block, Thomas Bogendoerfer, Martin K . Petersen,
Mike Snitzer, Geoff Levand, linuxppc-dev, ceph-devel, linux-mips,
Dongsheng Yang, linux-kernel, James E.J. Bottomley, dm-devel,
Andrew Morton, Ira Weiny, Ilya Dryomov
In-Reply-To: <20210727055646.118787-1-hch@lst.de>
These two helpers are entirely unused now.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
include/linux/bio.h | 42 ------------------------------------------
1 file changed, 42 deletions(-)
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 2203b686e1f0..7b5f65a81f2b 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -5,7 +5,6 @@
#ifndef __LINUX_BIO_H
#define __LINUX_BIO_H
-#include <linux/highmem.h>
#include <linux/mempool.h>
#include <linux/ioprio.h>
/* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */
@@ -519,47 +518,6 @@ static inline void bio_clone_blkg_association(struct bio *dst,
struct bio *src) { }
#endif /* CONFIG_BLK_CGROUP */
-#ifdef CONFIG_HIGHMEM
-/*
- * remember never ever reenable interrupts between a bvec_kmap_irq and
- * bvec_kunmap_irq!
- */
-static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags)
-{
- unsigned long addr;
-
- /*
- * might not be a highmem page, but the preempt/irq count
- * balancing is a lot nicer this way
- */
- local_irq_save(*flags);
- addr = (unsigned long) kmap_atomic(bvec->bv_page);
-
- BUG_ON(addr & ~PAGE_MASK);
-
- return (char *) addr + bvec->bv_offset;
-}
-
-static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags)
-{
- unsigned long ptr = (unsigned long) buffer & PAGE_MASK;
-
- kunmap_atomic((void *) ptr);
- local_irq_restore(*flags);
-}
-
-#else
-static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags)
-{
- return page_address(bvec->bv_page) + bvec->bv_offset;
-}
-
-static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags)
-{
- *flags = 0;
-}
-#endif
-
/*
* BIO list management for use by remapping drivers (e.g. DM or MD) and loop.
*
--
2.30.2
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox