The following changes since commit 3e08b2b9cb64bff2b73fa9128c0e49bfcde0dd40:

Merge remote-tracking branch 'remotes/philmd-gitlab/tags/edk2-next-20200121' into staging (2020-01-21 15:29:25 +0000)

https://github.com/rth7680/qemu.git tags/pull-tcg-20200121

for you to fetch changes up to 75fa376cdab5e5db2c7fdd107358e16f95503ac6:

scripts/git.orderfile: Display decodetree before C source (2020-01-21 15:26:09 -1000)

Remove another limit to NB_MMU_MODES.

Fix compilation using uclibc.

Fix defaulting of -accel parameters.

Tidy cputlb basic routines.

Adjust git.orderfile for decodetree.

Carlos Santos (1):

util/cacheinfo: fix crash when compiling with uClibc

Philippe Mathieu-Daudé (1):

scripts/git.orderfile: Display decodetree before C source

Richard Henderson (14):

cputlb: Handle NB_MMU_MODES > TARGET_PAGE_BITS_MIN

vl: Remove unused variable in configure_accelerators

vl: Reduce scope of variables in configure_accelerators

vl: Remove useless test in configure_accelerators

vl: Only choose enabled accelerators in configure_accelerators

cputlb: Merge tlb_table_flush_by_mmuidx into tlb_flush_one_mmuidx_locked

cputlb: Make tlb_n_entries private to cputlb.c

cputlb: Pass CPUTLBDescFast to tlb_n_entries and sizeof_tlb

cputlb: Hoist tlb portions in tlb_mmu_resize_locked

cputlb: Hoist tlb portions in tlb_flush_one_mmuidx_locked

cputlb: Split out tlb_mmu_flush_locked

cputlb: Partially merge tlb_dyn_init into tlb_init

cputlb: Initialize tlbs as flushed

cputlb: Hoist timestamp outside of loops over tlbs

include/exec/cpu_ldst.h | 5 -

accel/tcg/cputlb.c | 287 +++++++++++++++++++++++++++++++++---------------

util/cacheinfo.c | 10 +-

vl.c | 27 +++--

scripts/git.orderfile | 3 +

5 files changed, 223 insertions(+), 109 deletions(-)

Do not call get_clock_realtime() in tlb_mmu_resize_locked,

but hoist outside of any loop over a set of tlbs. This is

only two (indirect) callers, tlb_flush_by_mmuidx_async_work

and tlb_flush_page_locked, so not onerous.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Alistair Francis <alistair.francis@wdc.com>

Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>

accel/tcg/cputlb.c | 14 ++++++++------

1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c

--- a/accel/tcg/cputlb.c

+++ b/accel/tcg/cputlb.c

@@ -XXX,XX +XXX,XX @@ static void tlb_window_reset(CPUTLBDesc *desc, int64_t ns,

* high), since otherwise we are likely to have a significant amount of

* conflict misses.

*/

-static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast)

+static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast,

+ int64_t now)

{

size_t old_size = tlb_n_entries(fast);

size_t rate;

size_t new_size = old_size;

- int64_t now = get_clock_realtime();

int64_t window_len_ms = 100;

int64_t window_len_ns = window_len_ms * 1000 * 1000;

bool window_expired = now > desc->window_begin_ns + window_len_ns;

@@ -XXX,XX +XXX,XX @@ static void tlb_mmu_flush_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast)

memset(desc->vtable, -1, sizeof(desc->vtable));

-static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx)

+static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx,

+ int64_t now)

{

CPUTLBDesc *desc = &env_tlb(env)->d[mmu_idx];

CPUTLBDescFast *fast = &env_tlb(env)->f[mmu_idx];

- tlb_mmu_resize_locked(desc, fast);

+ tlb_mmu_resize_locked(desc, fast, now);

tlb_mmu_flush_locked(desc, fast);

@@ -XXX,XX +XXX,XX @@ static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data)

CPUArchState *env = cpu->env_ptr;

uint16_t asked = data.host_int;

uint16_t all_dirty, work, to_clean;

+ int64_t now = get_clock_realtime();

assert_cpu_is_self(cpu);

@@ -XXX,XX +XXX,XX @@ static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data)

for (work = to_clean; work != 0; work &= work - 1) {

int mmu_idx = ctz32(work);

- tlb_flush_one_mmuidx_locked(env, mmu_idx);

+ tlb_flush_one_mmuidx_locked(env, mmu_idx, now);

2.20.1

The result of g_strsplit is never NULL.

Acked-by: Paolo Bonzini <pbonzini@redhat.com>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>

Reviewed by: Aleksandar Markovic <amarkovic@wavecomp.com>

vl.c | 2 +-

diff --git a/vl.c b/vl.c

--- a/vl.c

+++ b/vl.c

@@ -XXX,XX +XXX,XX @@ static void configure_accelerators(const char *progname)

accel_list = g_strsplit(accel, ":", 0);

- for (tmp = accel_list; tmp && *tmp; tmp++) {

+ for (tmp = accel_list; *tmp; tmp++) {

/*

* Filter invalid accelerators here, to prevent obscenities

* such as "-machine accel=tcg,,thread=single".

2.20.1

From: Philippe Mathieu-Daudé <philmd@redhat.com>

To avoid scrolling each instruction when reviewing tcg

helpers written for the decodetree script, display the

.decode files (similar to header declarations) before

the C source (implementation of previous declarations).

Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

Message-Id: <20191230082856.30556-1-philmd@redhat.com>

scripts/git.orderfile | 3 +++

1 file changed, 3 insertions(+)

diff --git a/scripts/git.orderfile b/scripts/git.orderfile

--- a/scripts/git.orderfile

+++ b/scripts/git.orderfile

@@ -XXX,XX +XXX,XX @@ qga/*.json

# headers

*.h

+# decoding tree specification

+*.decode

# code

*.c

2.20.1

Merge into the only caller, but at the same time split

out tlb_mmu_init to initialize a single tlb entry.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Alistair Francis <alistair.francis@wdc.com>

Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>

accel/tcg/cputlb.c | 33 ++++++++++++++++-----------------

1 file changed, 16 insertions(+), 17 deletions(-)

@@ -XXX,XX +XXX,XX @@ static void tlb_window_reset(CPUTLBDesc *desc, int64_t ns,

desc->window_max_entries = max_entries;

-static void tlb_dyn_init(CPUArchState *env)

- int i;

-

- for (i = 0; i < NB_MMU_MODES; i++) {

- CPUTLBDesc *desc = &env_tlb(env)->d[i];

- size_t n_entries = 1 << CPU_TLB_DYN_DEFAULT_BITS;

-

- tlb_window_reset(desc, get_clock_realtime(), 0);

- desc->n_used_entries = 0;

- env_tlb(env)->f[i].mask = (n_entries - 1) << CPU_TLB_ENTRY_BITS;

- env_tlb(env)->f[i].table = g_new(CPUTLBEntry, n_entries);

- env_tlb(env)->d[i].iotlb = g_new(CPUIOTLBEntry, n_entries);

- }

/**

* tlb_mmu_resize_locked() - perform TLB resize bookkeeping; resize if necessary

* @desc: The CPUTLBDesc portion of the TLB

@@ -XXX,XX +XXX,XX @@ static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx)

tlb_mmu_flush_locked(desc, fast);

+static void tlb_mmu_init(CPUTLBDesc *desc, CPUTLBDescFast *fast, int64_t now)

+ size_t n_entries = 1 << CPU_TLB_DYN_DEFAULT_BITS;

+ tlb_window_reset(desc, now, 0);

+ desc->n_used_entries = 0;

+ fast->mask = (n_entries - 1) << CPU_TLB_ENTRY_BITS;

+ fast->table = g_new(CPUTLBEntry, n_entries);

+ desc->iotlb = g_new(CPUIOTLBEntry, n_entries);

static inline void tlb_n_used_entries_inc(CPUArchState *env, uintptr_t mmu_idx)

{

env_tlb(env)->d[mmu_idx].n_used_entries++;

@@ -XXX,XX +XXX,XX @@ static inline void tlb_n_used_entries_dec(CPUArchState *env, uintptr_t mmu_idx)

void tlb_init(CPUState *cpu)

{

CPUArchState *env = cpu->env_ptr;

+ int64_t now = get_clock_realtime();

+ int i;

qemu_spin_init(&env_tlb(env)->c.lock);

/* Ensure that cpu_reset performs a full flush. */

env_tlb(env)->c.dirty = ALL_MMUIDX_BITS;

- tlb_dyn_init(env);

+ for (i = 0; i < NB_MMU_MODES; i++) {

+ tlb_mmu_init(&env_tlb(env)->d[i], &env_tlb(env)->f[i], now);

+ }

}

/* flush_all_helper: run fn across all cpus

2.20.1

By choosing "tcg:kvm" when kvm is not enabled, we generate

an incorrect warning: "invalid accelerator kvm".

At the same time, use g_str_has_suffix rather than open-coding

the same operation.

Presumably the inverse is also true with --disable-tcg.

Fixes: 28a0961757fc

Acked-by: Paolo Bonzini <pbonzini@redhat.com>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

Reviewed by: Aleksandar Markovic <amarkovic@wavecomp.com>

vl.c | 21 +++++++++++++--------

1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/vl.c b/vl.c

--- a/vl.c

+++ b/vl.c

@@ -XXX,XX +XXX,XX @@ static void configure_accelerators(const char *progname)

if (accel == NULL) {

/* Select the default accelerator */

- if (!accel_find("tcg") && !accel_find("kvm")) {

- error_report("No accelerator selected and"

- " no default accelerator available");

- exit(1);

- } else {

- int pnlen = strlen(progname);

- if (pnlen >= 3 && g_str_equal(&progname[pnlen - 3], "kvm")) {

+ bool have_tcg = accel_find("tcg");

+ bool have_kvm = accel_find("kvm");

+

+ if (have_tcg && have_kvm) {

+ if (g_str_has_suffix(progname, "kvm")) {

/* If the program name ends with "kvm", we prefer KVM */

accel = "kvm:tcg";

} else {

accel = "tcg:kvm";

}

+ } else if (have_kvm) {

+ accel = "kvm";

+ } else if (have_tcg) {

+ accel = "tcg";

+ } else {

+ error_report("No accelerator selected and"

+ " no default accelerator available");

+ exit(1);

}

}

-

accel_list = g_strsplit(accel, ":", 0);

for (tmp = accel_list; *tmp; tmp++) {

2.20.1

There is only one caller for tlb_table_flush_by_mmuidx. Place

the result at the earlier line number, due to an expected user

in the near future.

accel/tcg/cputlb.c | 19 +++++++------------

1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c

--- a/accel/tcg/cputlb.c

+++ b/accel/tcg/cputlb.c

@@ -XXX,XX +XXX,XX @@ static void tlb_mmu_resize_locked(CPUArchState *env, int mmu_idx)

}

-static inline void tlb_table_flush_by_mmuidx(CPUArchState *env, int mmu_idx)

+static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx)

{

tlb_mmu_resize_locked(env, mmu_idx);

- memset(env_tlb(env)->f[mmu_idx].table, -1, sizeof_tlb(env, mmu_idx));

env_tlb(env)->d[mmu_idx].n_used_entries = 0;

+ env_tlb(env)->d[mmu_idx].large_page_addr = -1;

+ env_tlb(env)->d[mmu_idx].large_page_mask = -1;

+ env_tlb(env)->d[mmu_idx].vindex = 0;

+ memset(env_tlb(env)->f[mmu_idx].table, -1, sizeof_tlb(env, mmu_idx));

+ memset(env_tlb(env)->d[mmu_idx].vtable, -1,

+ sizeof(env_tlb(env)->d[0].vtable));

static inline void tlb_n_used_entries_inc(CPUArchState *env, uintptr_t mmu_idx)

@@ -XXX,XX +XXX,XX @@ void tlb_flush_counts(size_t *pfull, size_t *ppart, size_t *pelide)

*pelide = elide;

}

-static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx)

- tlb_table_flush_by_mmuidx(env, mmu_idx);

- env_tlb(env)->d[mmu_idx].large_page_addr = -1;

- env_tlb(env)->d[mmu_idx].large_page_mask = -1;

- env_tlb(env)->d[mmu_idx].vindex = 0;

- memset(env_tlb(env)->d[mmu_idx].vtable, -1,

- sizeof(env_tlb(env)->d[0].vtable));

static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data)

CPUArchState *env = cpu->env_ptr;

2.20.1

We will want to be able to flush a tlb without resizing.

Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>

accel/tcg/cputlb.c | 15 ++++++++++-----

1 file changed, 10 insertions(+), 5 deletions(-)

@@ -XXX,XX +XXX,XX @@ static void tlb_mmu_resize_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast)

}

-static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx)

+static void tlb_mmu_flush_locked(CPUTLBDesc *desc, CPUTLBDescFast *fast)

{

- CPUTLBDesc *desc = &env_tlb(env)->d[mmu_idx];

- CPUTLBDescFast *fast = &env_tlb(env)->f[mmu_idx];

- tlb_mmu_resize_locked(desc, fast);

desc->n_used_entries = 0;

desc->large_page_addr = -1;

desc->large_page_mask = -1;

@@ -XXX,XX +XXX,XX @@ static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx)

memset(desc->vtable, -1, sizeof(desc->vtable));

+static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx)

+ CPUTLBDesc *desc = &env_tlb(env)->d[mmu_idx];

+ CPUTLBDescFast *fast = &env_tlb(env)->f[mmu_idx];

+ tlb_mmu_resize_locked(desc, fast);

+ tlb_mmu_flush_locked(desc, fast);

static inline void tlb_n_used_entries_inc(CPUArchState *env, uintptr_t mmu_idx)

{

env_tlb(env)->d[mmu_idx].n_used_entries++;

2.20.1

We do not need the entire CPUArchState to compute these values.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

Reviewed-by: Alistair Francis <alistair.francis@wdc.com>

Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>

accel/tcg/cputlb.c | 15 ++++++++-------

1 file changed, 8 insertions(+), 7 deletions(-)

@@ -XXX,XX +XXX,XX @@ QEMU_BUILD_BUG_ON(sizeof(target_ulong) > sizeof(run_on_cpu_data));

QEMU_BUILD_BUG_ON(NB_MMU_MODES > 16);

#define ALL_MMUIDX_BITS ((1 << NB_MMU_MODES) - 1)

-static inline size_t tlb_n_entries(CPUArchState *env, uintptr_t mmu_idx)

+static inline size_t tlb_n_entries(CPUTLBDescFast *fast)

- return (env_tlb(env)->f[mmu_idx].mask >> CPU_TLB_ENTRY_BITS) + 1;

+ return (fast->mask >> CPU_TLB_ENTRY_BITS) + 1;

-static inline size_t sizeof_tlb(CPUArchState *env, uintptr_t mmu_idx)

+static inline size_t sizeof_tlb(CPUTLBDescFast *fast)

{

- return env_tlb(env)->f[mmu_idx].mask + (1 << CPU_TLB_ENTRY_BITS);

+ return fast->mask + (1 << CPU_TLB_ENTRY_BITS);

}

static void tlb_window_reset(CPUTLBDesc *desc, int64_t ns,

@@ -XXX,XX +XXX,XX @@ static void tlb_dyn_init(CPUArchState *env)

static void tlb_mmu_resize_locked(CPUArchState *env, int mmu_idx)

{

CPUTLBDesc *desc = &env_tlb(env)->d[mmu_idx];

- size_t old_size = tlb_n_entries(env, mmu_idx);

+ size_t old_size = tlb_n_entries(&env_tlb(env)->f[mmu_idx]);

size_t rate;

size_t new_size = old_size;

int64_t now = get_clock_realtime();

@@ -XXX,XX +XXX,XX @@ static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx)

env_tlb(env)->d[mmu_idx].large_page_addr = -1;

env_tlb(env)->d[mmu_idx].large_page_mask = -1;

env_tlb(env)->d[mmu_idx].vindex = 0;

- memset(env_tlb(env)->f[mmu_idx].table, -1, sizeof_tlb(env, mmu_idx));

+ memset(env_tlb(env)->f[mmu_idx].table, -1,

+ sizeof_tlb(&env_tlb(env)->f[mmu_idx]));

memset(env_tlb(env)->d[mmu_idx].vtable, -1,

sizeof(env_tlb(env)->d[0].vtable));

}

@@ -XXX,XX +XXX,XX @@ void tlb_reset_dirty(CPUState *cpu, ram_addr_t start1, ram_addr_t length)

qemu_spin_lock(&env_tlb(env)->c.lock);

for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {

unsigned int i;

- unsigned int n = tlb_n_entries(env, mmu_idx);

+ unsigned int n = tlb_n_entries(&env_tlb(env)->f[mmu_idx]);

for (i = 0; i < n; i++) {

tlb_reset_dirty_range_locked(&env_tlb(env)->f[mmu_idx].table[i],

2.20.1

The accel_list and tmp variables are only used when manufacturing

-machine accel, options based on -accel.

Acked-by: Paolo Bonzini <pbonzini@redhat.com>

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>

Reviewed by: Aleksandar Markovic <amarkovic@wavecomp.com>

vl.c | 3 ++-

1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/vl.c b/vl.c

--- a/vl.c

+++ b/vl.c

@@ -XXX,XX +XXX,XX @@ static int do_configure_accelerator(void *opaque, QemuOpts *opts, Error **errp)

static void configure_accelerators(const char *progname)

{

const char *accel;

- char **accel_list, **tmp;

bool init_failed = false;

qemu_opts_foreach(qemu_find_opts("icount"),

@@ -XXX,XX +XXX,XX @@ static void configure_accelerators(const char *progname)

accel = qemu_opt_get(qemu_get_machine_opts(), "accel");

if (QTAILQ_EMPTY(&qemu_accel_opts.head)) {

+ char **accel_list, **tmp;

+

if (accel == NULL) {

/* Select the default accelerator */